{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/sota/object-detection-on-coco","task":{"name":"Object Detection","url":"/task/object-detection","note":null},"dataset":{"name":"COCO test-dev","url":"/dataset/coco"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":null,"description_from":null,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["box mAP","AP50","AP75","APS","APM","APL","Hardware Burden","Params (M)","Operations per network pass","GFLOPs"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction; the tokens 'score' and 'time' are not used on this page); null = not inferred, chart draws points only","by_metric":{"box mAP":"higher","AP50":null,"AP75":null,"APS":null,"APM":null,"APL":null,"Hardware Burden":null,"Params (M)":"lower","Operations per network pass":null,"GFLOPs":null}},"counts":{"rows":225,"rows_with_code":220,"rows_with_paper_page":225,"rows_dated":225,"rows_using_additional_data":13},"rows":[{"rank_in_archive_order":1,"model":"Co-DETR","metrics":{"Params (M)":"304","box mAP":"66.0"},"uses_additional_data":false,"paper_date":"2022-11-22","paper":"/paper/detrs-with-collaborative-hybrid-assignments","paper_url":"https://arxiv.org/abs/2211.12860v5","paper_title":"DETRs with Collaborative Hybrid Assignments Training","code":"https://github.com/open-mmlab/mmdetection","n_code_links":6,"official":null,"syntology":{"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_samples":5,"n_pointer_only_licence":0,"sample_list":"/paper/detrs-with-collaborative-hybrid-assignments#ran","syntology_url":"https://syntology.ai/paper/2211.12860","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.12860"}}}},{"rank_in_archive_order":2,"model":"InternImage-H (M3I Pre-training)","metrics":{"Params (M)":"2180","box mAP":"65.5"},"uses_additional_data":false,"paper_date":"2022-11-10","paper":"/paper/internimage-exploring-large-scale-vision","paper_url":"https://arxiv.org/abs/2211.05778v4","paper_title":"InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions","code":"https://github.com/opengvlab/internimage","n_code_links":3,"official":{"repos":["opengvlab/internimage"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["listed"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":2,"n_samples":4,"n_pointer_only_licence":0,"sample_list":"/paper/internimage-exploring-large-scale-vision#ran","syntology_url":"https://syntology.ai/paper/2211.05778","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.05778"}}}},{"rank_in_archive_order":3,"model":"M3I Pre-training (InternImage-H)","metrics":{"box mAP":"65.4"},"uses_additional_data":false,"paper_date":"2022-11-17","paper":"/paper/towards-all-in-one-pre-training-via","paper_url":"https://arxiv.org/abs/2211.09807v2","paper_title":"Towards All-in-one Pre-training via Maximizing Multi-modal Mutual Information","code":"https://github.com/OpenGVLab/M3I-Pretraining","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":4,"model":"MoCaE","metrics":{"box mAP":"65.1"},"uses_additional_data":false,"paper_date":"2023-09-26","paper":"/paper/mocae-mixture-of-calibrated-experts","paper_url":"https://arxiv.org/abs/2309.14976v4","paper_title":"MoCaE: Mixture of Calibrated Experts Significantly Improves Object Detection","code":"https://github.com/fiveai/MoCaE","n_code_links":1,"official":{"repos":["fiveai/MoCaE"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]},"syntology":{"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1,"sample_list":"/paper/mocae-mixture-of-calibrated-experts#ran","syntology_url":"https://syntology.ai/paper/2309.14976","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.14976"}}}},{"rank_in_archive_order":5,"model":"Focal-Stable-DINO (Focal-Huge, no TTA)","metrics":{"AP50":"81.7","AP75":"71.5","APL":"78","APM":"67.6","APS":"48.6","Params (M)":"689","box mAP":"64.8"},"uses_additional_data":false,"paper_date":"2023-04-25","paper":"/paper/a-strong-and-reproducible-object-detector","paper_url":"https://arxiv.org/abs/2304.13027v1","paper_title":"A Strong and Reproducible Object Detector with Only Public Datasets","code":"https://github.com/microsoft/FocalNet","n_code_links":3,"official":null,"syntology":null},{"rank_in_archive_order":6,"model":"Co-DETR (Swin-L)","metrics":{"Params (M)":"218","box mAP":"64.8"},"uses_additional_data":false,"paper_date":"2022-11-22","paper":"/paper/detrs-with-collaborative-hybrid-assignments","paper_url":"https://arxiv.org/abs/2211.12860v5","paper_title":"DETRs with Collaborative Hybrid Assignments Training","code":"https://github.com/open-mmlab/mmdetection","n_code_links":6,"official":null,"syntology":{"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_samples":5,"n_pointer_only_licence":0,"sample_list":"/paper/detrs-with-collaborative-hybrid-assignments#ran","syntology_url":"https://syntology.ai/paper/2211.12860","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.12860"}}}},{"rank_in_archive_order":7,"model":"EVA","metrics":{"AP50":"81.9","AP75":"71.7","APL":"77.9","APM":"67.7","APS":"48.5","box mAP":"64.7"},"uses_additional_data":false,"paper_date":"2022-11-14","paper":"/paper/eva-exploring-the-limits-of-masked-visual","paper_url":"https://arxiv.org/abs/2211.07636v2","paper_title":"EVA: Exploring the Limits of Masked Visual Representation Learning at Scale","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":6,"official":{"repos":["baaivision/eva","rwightman/pytorch-image-models"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]},"syntology":{"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"n_samples":3,"n_pointer_only_licence":0,"sample_list":"/paper/eva-exploring-the-limits-of-masked-visual#ran","syntology_url":"https://syntology.ai/paper/2211.07636","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.07636"}}}},{"rank_in_archive_order":8,"model":"Group DETR v2","metrics":{"AP50":"81.8","AP75":"71.1","APL":"77.1","APM":"67.2","APS":"48.4","box mAP":"64.5"},"uses_additional_data":false,"paper_date":"2022-11-07","paper":"/paper/group-detr-v2-strong-object-detector-with-1","paper_url":"https://arxiv.org/abs/2211.03594v1","paper_title":"Group DETR v2: Strong Object Detector with Encoder-Decoder Pretraining","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":9,"model":"FocalNet-H (DINO)","metrics":{"box mAP":"64.4"},"uses_additional_data":false,"paper_date":"2022-03-22","paper":"/paper/focal-modulation-networks","paper_url":"https://arxiv.org/abs/2203.11926v3","paper_title":"Focal Modulation Networks","code":"https://github.com/PaddlePaddle/PaddleDetection","n_code_links":9,"official":{"repos":["microsoft/FocalNet"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0,"sample_list":"/paper/focal-modulation-networks#ran","syntology_url":"https://syntology.ai/paper/2203.11926","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.11926"}}}},{"rank_in_archive_order":10,"model":"InternImage-XL","metrics":{"Params (M)":"602","box mAP":"64.3"},"uses_additional_data":false,"paper_date":"2022-11-10","paper":"/paper/internimage-exploring-large-scale-vision","paper_url":"https://arxiv.org/abs/2211.05778v4","paper_title":"InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions","code":"https://github.com/opengvlab/internimage","n_code_links":3,"official":{"repos":["opengvlab/internimage"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["listed"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":2,"n_samples":4,"n_pointer_only_licence":0,"sample_list":"/paper/internimage-exploring-large-scale-vision#ran","syntology_url":"https://syntology.ai/paper/2211.05778","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.05778"}}}},{"rank_in_archive_order":11,"model":"FD-SwinV2-G","metrics":{"box mAP":"64.2"},"uses_additional_data":false,"paper_date":"2022-05-27","paper":"/paper/contrastive-learning-rivals-masked-image","paper_url":"https://arxiv.org/abs/2205.14141v3","paper_title":"Contrastive Learning Rivals Masked Image Modeling in Fine-tuning via Feature Distillation","code":"https://github.com/SwinTransformer/Feature-Distillation","n_code_links":1,"official":{"repos":["SwinTransformer/Feature-Distillation"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":5,"ran_from_kinds":["official"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":5,"n_samples":8,"n_pointer_only_licence":8,"sample_list":"/paper/contrastive-learning-rivals-masked-image#ran","syntology_url":"https://syntology.ai/paper/2205.14141","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.14141"}}}},{"rank_in_archive_order":12,"model":"Plain-DETR (Swin-L)","metrics":{"AP50":"82.1","AP75":"70.7","APL":"76.7","APM":"66.8","APS":"48.2","Params (M)":"228","box mAP":"63.9"},"uses_additional_data":false,"paper_date":"2023-01-01","paper":"/paper/detr-does-not-need-multi-scale-or-locality","paper_url":"http://openaccess.thecvf.com//content/ICCV2023/html/Lin_DETR_Does_Not_Need_Multi-Scale_or_Locality_Design_ICCV_2023_paper.html","paper_title":"DETR Does Not Need Multi-Scale or Locality Design","code":"https://github.com/impiga/plain-detr","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":13,"model":"RevCol-H(DINO)","metrics":{"box mAP":"63.8"},"uses_additional_data":false,"paper_date":"2022-12-22","paper":"/paper/reversible-column-networks","paper_url":"https://arxiv.org/abs/2212.11696v3","paper_title":"Reversible Column Networks","code":"https://github.com/megvii-research/revcol","n_code_links":1,"official":{"repos":["megvii-research/revcol"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":8,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]},"syntology":{"n_ran":8,"n_constructed":8,"n_ran_checked":8,"n_instrument":0,"n_unverified":3,"n_samples":11,"n_pointer_only_licence":0,"sample_list":"/paper/reversible-column-networks#ran","syntology_url":"https://syntology.ai/paper/2212.11696","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.11696"}}}},{"rank_in_archive_order":14,"model":"BEiT-3","metrics":{"box mAP":"63.7"},"uses_additional_data":false,"paper_date":"2022-08-22","paper":"/paper/image-as-a-foreign-language-beit-pretraining","paper_url":"https://arxiv.org/abs/2208.10442v2","paper_title":"Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Tasks","code":"https://github.com/microsoft/unilm/tree/master/beit","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":15,"model":"Relation-DETR (Focal-L)","metrics":{"AP50":"80.8","AP75":"69.1","APL":"77.0","APM":"66.9","APS":"47.2","Params (M)":"214","box mAP":"63.5"},"uses_additional_data":false,"paper_date":"2024-07-16","paper":"/paper/relation-detr-exploring-explicit-position","paper_url":"https://arxiv.org/abs/2407.11699v1","paper_title":"Relation DETR: Exploring Explicit Position Relation Prior for Object Detection","code":"https://github.com/xiuqhou/relation-detr","n_code_links":2,"official":{"repos":["xiuqhou/relation-detr"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]},"syntology":{"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0,"sample_list":"/paper/relation-detr-exploring-explicit-position#ran","syntology_url":"https://syntology.ai/paper/2407.11699","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.11699"}}}},{"rank_in_archive_order":16,"model":"DETA (Swin-L)","metrics":{"AP50":"80.4","AP75":"70.2","APL":"76.9","APM":"66.9","APS":"46.1","box mAP":"63.5"},"uses_additional_data":false,"paper_date":"2022-12-12","paper":"/paper/nms-strikes-back","paper_url":"https://arxiv.org/abs/2212.06137v1","paper_title":"NMS Strikes Back","code":"https://github.com/jozhang97/deta","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":17,"model":"DINO (Swin-L,multi-scale, TTA)","metrics":{"box mAP":"63.3"},"uses_additional_data":false,"paper_date":"2022-03-07","paper":"/paper/dino-detr-with-improved-denoising-anchor-1","paper_url":"https://arxiv.org/abs/2203.03605v4","paper_title":"DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection","code":"https://github.com/IDEA-Research/Grounded-Segment-Anything","n_code_links":16,"official":{"repos":["IDEACVR/DINO"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":10,"n_constructed":0,"n_ran_checked":2,"n_instrument":8,"n_unverified":5,"n_samples":15,"n_pointer_only_licence":5,"sample_list":"/paper/dino-detr-with-improved-denoising-anchor-1#ran","syntology_url":"https://syntology.ai/paper/2203.03605","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.03605"}}}},{"rank_in_archive_order":18,"model":"SwinV2-G (HTC++)","metrics":{"Params (M)":"3000","box mAP":"63.1"},"uses_additional_data":false,"paper_date":"2021-11-18","paper":"/paper/swin-transformer-v2-scaling-up-capacity-and","paper_url":"https://arxiv.org/abs/2111.09883v2","paper_title":"Swin Transformer V2: Scaling Up Capacity and Resolution","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":23,"official":{"repos":["microsoft/Swin-Transformer"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":17,"n_constructed":0,"n_ran_checked":14,"n_instrument":3,"n_unverified":13,"n_samples":30,"n_pointer_only_licence":4,"sample_list":"/paper/swin-transformer-v2-scaling-up-capacity-and#ran","syntology_url":"https://syntology.ai/paper/2111.09883","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.09883"}}}},{"rank_in_archive_order":19,"model":"Grounding DINO","metrics":{"box mAP":"63.0"},"uses_additional_data":false,"paper_date":"2023-03-09","paper":"/paper/grounding-dino-marrying-dino-with-grounded","paper_url":"https://arxiv.org/abs/2303.05499v5","paper_title":"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection","code":"https://github.com/huggingface/transformers","n_code_links":10,"official":{"repos":["idea-research/groundingdino"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":3,"n_samples":5,"n_pointer_only_licence":0,"sample_list":"/paper/grounding-dino-marrying-dino-with-grounded#ran","syntology_url":"https://syntology.ai/paper/2303.05499","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.05499"}}}},{"rank_in_archive_order":20,"model":"Florence-CoSwin-H","metrics":{"box mAP":"62.4"},"uses_additional_data":false,"paper_date":"2021-11-22","paper":"/paper/florence-a-new-foundation-model-for-computer","paper_url":"https://arxiv.org/abs/2111.11432v1","paper_title":"Florence: A New Foundation Model for Computer Vision","code":"https://github.com/microsoft/unicl","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":21,"model":"GLIPv2 (CoSwin-H, multi-scale)","metrics":{"box mAP":"62.4"},"uses_additional_data":false,"paper_date":"2022-06-12","paper":"/paper/glipv2-unifying-localization-and-vision","paper_url":"https://arxiv.org/abs/2206.05836v2","paper_title":"GLIPv2: Unifying Localization and Vision-Language Understanding","code":"https://github.com/microsoft/GLIP","n_code_links":1,"official":{"repos":["microsoft/GLIP"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0,"sample_list":"/paper/glipv2-unifying-localization-and-vision#ran","syntology_url":"https://syntology.ai/paper/2206.05836","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.05836"}}}},{"rank_in_archive_order":22,"model":"GLEE-Pro","metrics":{"box mAP":"62.3"},"uses_additional_data":false,"paper_date":"2023-12-14","paper":"/paper/general-object-foundation-model-for-images","paper_url":"https://arxiv.org/abs/2312.09158v1","paper_title":"General Object Foundation Model for Images and Videos at Scale","code":"https://github.com/FoundationVision/GLEE","n_code_links":1,"official":{"repos":["FoundationVision/GLEE"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]},"syntology":{"n_ran":11,"n_constructed":0,"n_ran_checked":2,"n_instrument":9,"n_unverified":2,"n_samples":13,"n_pointer_only_licence":3,"sample_list":"/paper/general-object-foundation-model-for-images#ran","syntology_url":"https://syntology.ai/paper/2312.09158","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.09158"}}}},{"rank_in_archive_order":23,"model":"GLIP (Swin-L, multi-scale)","metrics":{"AP50":"79.5","AP75":"67.7","APL":"75.0","APM":"64.9","APS":"45.3","box mAP":"61.5"},"uses_additional_data":false,"paper_date":"2021-12-07","paper":"/paper/grounded-language-image-pre-training","paper_url":"https://arxiv.org/abs/2112.03857v2","paper_title":"Grounded Language-Image Pre-training","code":"https://github.com/microsoft/GLIP","n_code_links":3,"official":{"repos":["microsoft/GLIP"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2,"sample_list":"/paper/grounded-language-image-pre-training#ran","syntology_url":"https://syntology.ai/paper/2112.03857","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.03857"}}}},{"rank_in_archive_order":24,"model":"Soft Teacher + Swin-L (HTC++, multi-scale)","metrics":{"box mAP":"61.3"},"uses_additional_data":false,"paper_date":"2021-06-16","paper":"/paper/end-to-end-semi-supervised-object-detection","paper_url":"https://arxiv.org/abs/2106.09018v3","paper_title":"End-to-End Semi-Supervised Object Detection with Soft Teacher","code":"https://github.com/microsoft/SoftTeacher","n_code_links":8,"official":null,"syntology":null},{"rank_in_archive_order":25,"model":"ViT-Adapter-L (HTC++, BEiTv2 pretrain, multi-scale)","metrics":{"box mAP":"60.9"},"uses_additional_data":false,"paper_date":"2022-05-17","paper":"/paper/vision-transformer-adapter-for-dense","paper_url":"https://arxiv.org/abs/2205.08534v4","paper_title":"Vision Transformer Adapter for Dense Predictions","code":"https://github.com/czczup/vit-adapter","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":26,"model":"DyHead (Swin-L, multi scale, self-training)","metrics":{"AP50":"78.5","AP75":"66.6","APL":"74.2","APM":"64.0","box mAP":"60.6"},"uses_additional_data":false,"paper_date":"2021-06-15","paper":"/paper/dynamic-head-unifying-object-detection-heads","paper_url":"https://arxiv.org/abs/2106.08322v1","paper_title":"Dynamic Head: Unifying Object Detection Heads with Attentions","code":"https://github.com/open-mmlab/mmdetection","n_code_links":3,"official":{"repos":["microsoft/DynamicHead"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":8,"n_constructed":5,"n_ran_checked":6,"n_instrument":2,"n_unverified":1,"n_samples":9,"n_pointer_only_licence":0,"sample_list":"/paper/dynamic-head-unifying-object-detection-heads#ran","syntology_url":"https://syntology.ai/paper/2106.08322","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.08322"}}}},{"rank_in_archive_order":27,"model":"GLEE-Plus","metrics":{"box mAP":"60.6"},"uses_additional_data":false,"paper_date":"2023-12-14","paper":"/paper/general-object-foundation-model-for-images","paper_url":"https://arxiv.org/abs/2312.09158v1","paper_title":"General Object Foundation Model for Images and Videos at Scale","code":"https://github.com/FoundationVision/GLEE","n_code_links":1,"official":{"repos":["FoundationVision/GLEE"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]},"syntology":{"n_ran":11,"n_constructed":0,"n_ran_checked":2,"n_instrument":9,"n_unverified":2,"n_samples":13,"n_pointer_only_licence":3,"sample_list":"/paper/general-object-foundation-model-for-images#ran","syntology_url":"https://syntology.ai/paper/2312.09158","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.09158"}}}},{"rank_in_archive_order":28,"model":"ViT-Adapter-L (HTC++, BEiT pretrain, multi-scale)","metrics":{"box mAP":"60.4"},"uses_additional_data":false,"paper_date":"2022-05-17","paper":"/paper/vision-transformer-adapter-for-dense","paper_url":"https://arxiv.org/abs/2205.08534v4","paper_title":"Vision Transformer Adapter for Dense Predictions","code":"https://github.com/czczup/vit-adapter","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":29,"model":"GRiT (ViT-H, single-scale testing)","metrics":{"box mAP":"60.4"},"uses_additional_data":false,"paper_date":"2022-12-01","paper":"/paper/grit-a-generative-region-to-text-transformer","paper_url":"https://arxiv.org/abs/2212.00280v1","paper_title":"GRiT: A Generative Region-to-text Transformer for Object Understanding","code":"https://github.com/JialianW/GRiT","n_code_links":1,"official":{"repos":["JialianW/GRiT"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]},"syntology":{"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":2,"n_samples":8,"n_pointer_only_licence":8,"sample_list":"/paper/grit-a-generative-region-to-text-transformer#ran","syntology_url":"https://syntology.ai/paper/2212.00280","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.00280"}}}},{"rank_in_archive_order":30,"model":"CBNetV2 (Dual-Swin-L HTC, multi-scale)","metrics":{"box mAP":"60.1"},"uses_additional_data":false,"paper_date":"2021-07-01","paper":"/paper/cbnetv2-a-composite-backbone-network","paper_url":"https://arxiv.org/abs/2107.00420v7","paper_title":"CBNet: A Composite Backbone Network Architecture for Object Detection","code":"https://github.com/PaddlePaddle/PaddleDetection","n_code_links":4,"official":{"repos":["VDIGPKU/CBNetV2"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_samples":3,"n_pointer_only_licence":2,"sample_list":"/paper/cbnetv2-a-composite-backbone-network#ran","syntology_url":"https://syntology.ai/paper/2107.00420","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.00420"}}}},{"rank_in_archive_order":31,"model":"PIIP-H6B (DINO)","metrics":{"AP50":"79.0","AP75":"65.4","box mAP":"60.0"},"uses_additional_data":false,"paper_date":"2024-06-06","paper":"/paper/parameter-inverted-image-pyramid-networks","paper_url":"https://arxiv.org/abs/2406.04330v2","paper_title":"Parameter-Inverted Image Pyramid Networks","code":"https://github.com/opengvlab/piip","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":32,"model":"CBNetV2 (Dual-Swin-L HTC, single-scale)","metrics":{"box mAP":"59.4"},"uses_additional_data":false,"paper_date":"2021-07-01","paper":"/paper/cbnetv2-a-composite-backbone-network","paper_url":"https://arxiv.org/abs/2107.00420v7","paper_title":"CBNet: A Composite Backbone Network Architecture for Object Detection","code":"https://github.com/PaddlePaddle/PaddleDetection","n_code_links":4,"official":{"repos":["VDIGPKU/CBNetV2"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_samples":3,"n_pointer_only_licence":2,"sample_list":"/paper/cbnetv2-a-composite-backbone-network#ran","syntology_url":"https://syntology.ai/paper/2107.00420","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.00420"}}}},{"rank_in_archive_order":33,"model":"Focal-L (DyHead, multi-scale)","metrics":{"box mAP":"58.9"},"uses_additional_data":false,"paper_date":"2021-07-01","paper":"/paper/focal-self-attention-for-local-global","paper_url":"https://arxiv.org/abs/2107.00641v1","paper_title":"Focal Self-attention for Local-Global Interactions in Vision Transformers","code":"https://github.com/BR-IDL/PaddleViT/tree/develop/image_classification/Focal_Transformer","n_code_links":3,"official":{"repos":["microsoft/Focal-Transformer"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":2,"sample_list":"/paper/focal-self-attention-for-local-global#ran","syntology_url":"https://syntology.ai/paper/2107.00641","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.00641"}}}},{"rank_in_archive_order":34,"model":"DyHead (Swin-L, multi scale)","metrics":{"AP50":"77.1","AP75":"64.5","APL":"72.8","APM":"62.0","box mAP":"58.7"},"uses_additional_data":false,"paper_date":"2021-06-15","paper":"/paper/dynamic-head-unifying-object-detection-heads","paper_url":"https://arxiv.org/abs/2106.08322v1","paper_title":"Dynamic Head: Unifying Object Detection Heads with Attentions","code":"https://github.com/open-mmlab/mmdetection","n_code_links":3,"official":{"repos":["microsoft/DynamicHead"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":8,"n_constructed":5,"n_ran_checked":6,"n_instrument":2,"n_unverified":1,"n_samples":9,"n_pointer_only_licence":0,"sample_list":"/paper/dynamic-head-unifying-object-detection-heads#ran","syntology_url":"https://syntology.ai/paper/2106.08322","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.08322"}}}},{"rank_in_archive_order":35,"model":"Swin-L (HTC++, multi scale)","metrics":{"box mAP":"58.7"},"uses_additional_data":false,"paper_date":"2021-03-25","paper":"/paper/swin-transformer-hierarchical-vision","paper_url":"https://arxiv.org/abs/2103.14030v2","paper_title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","code":"https://github.com/huggingface/transformers","n_code_links":80,"official":{"repos":["microsoft/Swin-Transformer"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["listed"]},"syntology":{"n_ran":123,"n_constructed":45,"n_ran_checked":79,"n_instrument":44,"n_unverified":84,"n_samples":207,"n_pointer_only_licence":45,"sample_list":"/paper/swin-transformer-hierarchical-vision#ran","syntology_url":"https://syntology.ai/paper/2103.14030","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.14030"}}}},{"rank_in_archive_order":36,"model":"Swin-L (HTC++, single scale)","metrics":{"box mAP":"57.7"},"uses_additional_data":false,"paper_date":"2021-03-25","paper":"/paper/swin-transformer-hierarchical-vision","paper_url":"https://arxiv.org/abs/2103.14030v2","paper_title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","code":"https://github.com/huggingface/transformers","n_code_links":80,"official":{"repos":["microsoft/Swin-Transformer"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["listed"]},"syntology":{"n_ran":123,"n_constructed":45,"n_ran_checked":79,"n_instrument":44,"n_unverified":84,"n_samples":207,"n_pointer_only_licence":45,"sample_list":"/paper/swin-transformer-hierarchical-vision#ran","syntology_url":"https://syntology.ai/paper/2103.14030","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.14030"}}}},{"rank_in_archive_order":37,"model":"Cascade Eff-B7 NAS-FPN (1280, self-training Copy Paste, single-scale)","metrics":{"box mAP":"57.3"},"uses_additional_data":false,"paper_date":"2020-12-13","paper":"/paper/simple-copy-paste-is-a-strong-data","paper_url":"https://arxiv.org/abs/2012.07177v2","paper_title":"Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation","code":"https://github.com/PaddlePaddle/PaddleOCR","n_code_links":5,"official":{"repos":["tensorflow/tpu"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0,"sample_list":"/paper/simple-copy-paste-is-a-strong-data#ran","syntology_url":"https://syntology.ai/paper/2012.07177","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2012.07177"}}}},{"rank_in_archive_order":38,"model":"PyCenterNet (Swin-L, multi-scale)","metrics":{"AP50":"73.7","AP75":"62.4","APL":"71.3","APM":"59.2","APS":"38.7","box mAP":"57.1"},"uses_additional_data":false,"paper_date":"2022-04-18","paper":"/paper/centernet-for-object-detection","paper_url":"https://arxiv.org/abs/2204.08394v1","paper_title":"CenterNet++ for Object Detection","code":"https://github.com/Duankaiwen/PyCenterNet","n_code_links":3,"official":null,"syntology":null},{"rank_in_archive_order":39,"model":"dBOT ViT-L (CLIP)","metrics":{"box mAP":"56.8"},"uses_additional_data":false,"paper_date":"2022-09-08","paper":"/paper/exploring-target-representations-for-masked","paper_url":"https://arxiv.org/abs/2209.03917v3","paper_title":"Exploring Target Representations for Masked Autoencoders","code":"https://github.com/liuxingbin/dbot","n_code_links":1,"official":{"repos":["liuxingbin/dbot"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":2,"ran_from_kinds":["official"]},"syntology":{"n_ran":11,"n_constructed":0,"n_ran_checked":10,"n_instrument":1,"n_unverified":2,"n_samples":13,"n_pointer_only_licence":2,"sample_list":"/paper/exploring-target-representations-for-masked#ran","syntology_url":"https://syntology.ai/paper/2209.03917","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.03917"}}}},{"rank_in_archive_order":40,"model":"YOLOv7-D6 (44 fps)","metrics":{"box mAP":"56.6"},"uses_additional_data":true,"paper_date":"2022-07-06","paper":"/paper/yolov7-trainable-bag-of-freebies-sets-new","paper_url":"https://arxiv.org/abs/2207.02696v1","paper_title":"YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors","code":"https://github.com/pjreddie/darknet","n_code_links":21,"official":{"repos":["wongkinyiu/yolov7"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":10,"n_constructed":0,"n_ran_checked":8,"n_instrument":2,"n_unverified":1,"n_samples":11,"n_pointer_only_licence":5,"sample_list":"/paper/yolov7-trainable-bag-of-freebies-sets-new#ran","syntology_url":"https://syntology.ai/paper/2207.02696","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.02696"}}}},{"rank_in_archive_order":41,"model":"SOLQ (Swin-L, single scale)","metrics":{"AP50":"74.6","AP75":"60.5","APL":"70.6","APM":"60","APS":"37.6","box mAP":"56.5"},"uses_additional_data":false,"paper_date":"2021-06-04","paper":"/paper/solq-segmenting-objects-by-learning-queries","paper_url":"https://arxiv.org/abs/2106.02351v3","paper_title":"SOLQ: Segmenting Objects by Learning Queries","code":"https://github.com/megvii-research/SOLQ","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":42,"model":"CenterNet2 (Res2Net-101-DCN-BiFPN, self-training, 1560 single-scale)","metrics":{"AP50":"74.0","AP75":"61.6","APL":"68.6","APM":"59.7","APS":"38.7","box mAP":"56.4"},"uses_additional_data":false,"paper_date":"2021-03-12","paper":"/paper/probabilistic-two-stage-detection","paper_url":"https://arxiv.org/abs/2103.07461v1","paper_title":"Probabilistic two-stage detection","code":"https://github.com/xingyizhou/CenterNet2","n_code_links":3,"official":null,"syntology":null},{"rank_in_archive_order":43,"model":"ISTR (ResNet50-FPN-3x, single-scale)","metrics":{"APL":"59.9","APM":"48.7","APS":"27.8","box mAP":"56.4"},"uses_additional_data":false,"paper_date":"2021-05-03","paper":"/paper/istr-end-to-end-instance-segmentation-with","paper_url":"https://arxiv.org/abs/2105.00637v2","paper_title":"ISTR: End-to-End Instance Segmentation with Transformers","code":"https://github.com/hujiecpp/ISTR","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":44,"model":"QueryInst (single-scale)","metrics":{"AP50":"75.9","AP75":"61.9","APL":"70.3","APM":"58.9","APS":"37.4","Hardware Burden":"17G","box mAP":"56.1"},"uses_additional_data":false,"paper_date":"2021-05-05","paper":"/paper/queryinst-parallelly-supervised-mask-query","paper_url":"https://arxiv.org/abs/2105.01928v3","paper_title":"Instances as Queries","code":"https://github.com/open-mmlab/mmdetection","n_code_links":5,"official":{"repos":["hustvl/QueryInst"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_samples":3,"n_pointer_only_licence":1,"sample_list":"/paper/queryinst-parallelly-supervised-mask-query#ran","syntology_url":"https://syntology.ai/paper/2105.01928","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.01928"}}}},{"rank_in_archive_order":45,"model":"dBOT ViT-L","metrics":{"box mAP":"56.1"},"uses_additional_data":false,"paper_date":"2022-09-08","paper":"/paper/exploring-target-representations-for-masked","paper_url":"https://arxiv.org/abs/2209.03917v3","paper_title":"Exploring Target Representations for Masked Autoencoders","code":"https://github.com/liuxingbin/dbot","n_code_links":1,"official":{"repos":["liuxingbin/dbot"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":2,"ran_from_kinds":["official"]},"syntology":{"n_ran":11,"n_constructed":0,"n_ran_checked":10,"n_instrument":1,"n_unverified":2,"n_samples":13,"n_pointer_only_licence":2,"sample_list":"/paper/exploring-target-representations-for-masked#ran","syntology_url":"https://syntology.ai/paper/2209.03917","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.03917"}}}},{"rank_in_archive_order":46,"model":"YOLOv7-E6 (56 fps)","metrics":{"box mAP":"56"},"uses_additional_data":false,"paper_date":"2022-07-06","paper":"/paper/yolov7-trainable-bag-of-freebies-sets-new","paper_url":"https://arxiv.org/abs/2207.02696v1","paper_title":"YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors","code":"https://github.com/pjreddie/darknet","n_code_links":21,"official":{"repos":["wongkinyiu/yolov7"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":10,"n_constructed":0,"n_ran_checked":8,"n_instrument":2,"n_unverified":1,"n_samples":11,"n_pointer_only_licence":5,"sample_list":"/paper/yolov7-trainable-bag-of-freebies-sets-new#ran","syntology_url":"https://syntology.ai/paper/2207.02696","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.02696"}}}},{"rank_in_archive_order":47,"model":"YOLOv4-P7 with TTA","metrics":{"AP50":"73.2","AP75":"61.2","box mAP":"55.8"},"uses_additional_data":false,"paper_date":"2020-11-16","paper":"/paper/scaled-yolov4-scaling-cross-stage-partial","paper_url":"https://arxiv.org/abs/2011.08036v2","paper_title":"Scaled-YOLOv4: Scaling Cross Stage Partial Network","code":"https://github.com/AlexeyAB/darknet","n_code_links":41,"official":{"repos":["WongKinYiu/ScaledYOLOv4"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]},"syntology":{"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1,"sample_list":"/paper/scaled-yolov4-scaling-cross-stage-partial#ran","syntology_url":"https://syntology.ai/paper/2011.08036","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2011.08036"}}}},{"rank_in_archive_order":48,"model":"DetectoRS (ResNeXt-101-64x4d, multi-scale)","metrics":{"AP50":"74.2","AP75":"61.1","APL":"68.1","APM":"58.4","APS":"37.7","box mAP":"55.7"},"uses_additional_data":false,"paper_date":"2020-06-03","paper":"/paper/detectors-detecting-objects-with-recursive-1","paper_url":"https://arxiv.org/abs/2006.02334v2","paper_title":"DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolution","code":"https://github.com/open-mmlab/mmdetection","n_code_links":6,"official":{"repos":["joe-siyuan-qiao/DetectoRS"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_samples":4,"n_pointer_only_licence":0,"sample_list":"/paper/detectors-detecting-objects-with-recursive-1#ran","syntology_url":"https://syntology.ai/paper/2006.02334","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.02334"}}}},{"rank_in_archive_order":49,"model":"YOLOR-D6 (1280, single-scale, 30 fps)","metrics":{"AP50":"73.3","AP75":"60.6","box mAP":"55.4"},"uses_additional_data":false,"paper_date":"2021-05-10","paper":"/paper/you-only-learn-one-representation-unified","paper_url":"https://arxiv.org/abs/2105.04206v1","paper_title":"You Only Learn One Representation: Unified Network for Multiple Tasks","code":"https://github.com/WongKinYiu/yolor","n_code_links":9,"official":null,"syntology":null},{"rank_in_archive_order":50,"model":"YOLOv4-P6 with TTA","metrics":{"AP50":"72.6","AP75":"60.2","box mAP":"54.9"},"uses_additional_data":false,"paper_date":"2020-11-16","paper":"/paper/scaled-yolov4-scaling-cross-stage-partial","paper_url":"https://arxiv.org/abs/2011.08036v2","paper_title":"Scaled-YOLOv4: Scaling Cross Stage Partial Network","code":"https://github.com/AlexeyAB/darknet","n_code_links":41,"official":{"repos":["WongKinYiu/ScaledYOLOv4"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]},"syntology":{"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1,"sample_list":"/paper/scaled-yolov4-scaling-cross-stage-partial#ran","syntology_url":"https://syntology.ai/paper/2011.08036","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2011.08036"}}}},{"rank_in_archive_order":51,"model":"YOLOv7-W6 (84 fps)","metrics":{"box mAP":"54.9"},"uses_additional_data":false,"paper_date":"2022-07-06","paper":"/paper/yolov7-trainable-bag-of-freebies-sets-new","paper_url":"https://arxiv.org/abs/2207.02696v1","paper_title":"YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors","code":"https://github.com/pjreddie/darknet","n_code_links":21,"official":{"repos":["wongkinyiu/yolov7"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":10,"n_constructed":0,"n_ran_checked":8,"n_instrument":2,"n_unverified":1,"n_samples":11,"n_pointer_only_licence":5,"sample_list":"/paper/yolov7-trainable-bag-of-freebies-sets-new#ran","syntology_url":"https://syntology.ai/paper/2207.02696","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.02696"}}}},{"rank_in_archive_order":52,"model":"Cascade Eff-B7 NAS-FPN (1280)","metrics":{"box mAP":"54.8"},"uses_additional_data":false,"paper_date":"2020-12-13","paper":"/paper/simple-copy-paste-is-a-strong-data","paper_url":"https://arxiv.org/abs/2012.07177v2","paper_title":"Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation","code":"https://github.com/PaddlePaddle/PaddleOCR","n_code_links":5,"official":{"repos":["tensorflow/tpu"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0,"sample_list":"/paper/simple-copy-paste-is-a-strong-data#ran","syntology_url":"https://syntology.ai/paper/2012.07177","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2012.07177"}}}},{"rank_in_archive_order":53,"model":"DetectoRS (ResNeXt-101-32x4d, multi-scale)","metrics":{"AP50":"73.5","AP75":"60.1","APL":"66.4","APM":"57.3","APS":"37.4","box mAP":"54.7"},"uses_additional_data":false,"paper_date":"2020-06-03","paper":"/paper/detectors-detecting-objects-with-recursive-1","paper_url":"https://arxiv.org/abs/2006.02334v2","paper_title":"DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolution","code":"https://github.com/open-mmlab/mmdetection","n_code_links":6,"official":{"repos":["joe-siyuan-qiao/DetectoRS"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_samples":4,"n_pointer_only_licence":0,"sample_list":"/paper/detectors-detecting-objects-with-recursive-1#ran","syntology_url":"https://syntology.ai/paper/2006.02334","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.02334"}}}},{"rank_in_archive_order":54,"model":"GLEE-Lite","metrics":{"box mAP":"54.7"},"uses_additional_data":false,"paper_date":"2023-12-14","paper":"/paper/general-object-foundation-model-for-images","paper_url":"https://arxiv.org/abs/2312.09158v1","paper_title":"General Object Foundation Model for Images and Videos at Scale","code":"https://github.com/FoundationVision/GLEE","n_code_links":1,"official":{"repos":["FoundationVision/GLEE"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]},"syntology":{"n_ran":11,"n_constructed":0,"n_ran_checked":2,"n_instrument":9,"n_unverified":2,"n_samples":13,"n_pointer_only_licence":3,"sample_list":"/paper/general-object-foundation-model-for-images#ran","syntology_url":"https://syntology.ai/paper/2312.09158","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.09158"}}}},{"rank_in_archive_order":55,"model":"YOLOv4-P6 CSP-P6 (single-scale, 32 fps)","metrics":{"AP50":"72.3","AP75":"59.5","APL":"65.5","APM":"58.2","APS":"36.6","box mAP":"54.3"},"uses_additional_data":false,"paper_date":"2020-11-16","paper":"/paper/scaled-yolov4-scaling-cross-stage-partial","paper_url":"https://arxiv.org/abs/2011.08036v2","paper_title":"Scaled-YOLOv4: Scaling Cross Stage Partial Network","code":"https://github.com/AlexeyAB/darknet","n_code_links":41,"official":{"repos":["WongKinYiu/ScaledYOLOv4"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]},"syntology":{"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1,"sample_list":"/paper/scaled-yolov4-scaling-cross-stage-partial#ran","syntology_url":"https://syntology.ai/paper/2011.08036","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2011.08036"}}}},{"rank_in_archive_order":56,"model":"SpineNet-190 (1280, with Self-training on OpenImages, single-scale)","metrics":{"box mAP":"54.3"},"uses_additional_data":false,"paper_date":"2020-06-11","paper":"/paper/rethinking-pre-training-and-self-training","paper_url":"https://arxiv.org/abs/2006.06882v2","paper_title":"Rethinking Pre-training and Self-training","code":"https://github.com/tensorflow/tpu/tree/master/models/official/detection/projects/self_training","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":57,"model":"UniverseNet-20.08d (Res2Net-101, DCN, multi-scale)","metrics":{"AP50":"71.6","AP75":"59.9","APL":"67.4","APM":"57.2","APS":"35.8","box mAP":"54.1"},"uses_additional_data":false,"paper_date":"2021-03-25","paper":"/paper/usb-universal-scale-object-detection","paper_url":"https://arxiv.org/abs/2103.14027v3","paper_title":"USB: Universal-Scale Object Detection Benchmark","code":"https://github.com/shinya7y/UniverseNet","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":58,"model":"DyHead (ResNeXt-64x4d-101-DCN, multi scale)","metrics":{"AP50":"72.1","AP75":"59.3","box mAP":"54"},"uses_additional_data":false,"paper_date":"2021-06-15","paper":"/paper/dynamic-head-unifying-object-detection-heads","paper_url":"https://arxiv.org/abs/2106.08322v1","paper_title":"Dynamic Head: Unifying Object Detection Heads with Attentions","code":"https://github.com/open-mmlab/mmdetection","n_code_links":3,"official":{"repos":["microsoft/DynamicHead"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":8,"n_constructed":5,"n_ran_checked":6,"n_instrument":2,"n_unverified":1,"n_samples":9,"n_pointer_only_licence":0,"sample_list":"/paper/dynamic-head-unifying-object-detection-heads#ran","syntology_url":"https://syntology.ai/paper/2106.08322","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.08322"}}}},{"rank_in_archive_order":59,"model":"dBOT ViT-B (CLIP)","metrics":{"box mAP":"53.6"},"uses_additional_data":false,"paper_date":"2022-09-08","paper":"/paper/exploring-target-representations-for-masked","paper_url":"https://arxiv.org/abs/2209.03917v3","paper_title":"Exploring Target Representations for Masked Autoencoders","code":"https://github.com/liuxingbin/dbot","n_code_links":1,"official":{"repos":["liuxingbin/dbot"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":2,"ran_from_kinds":["official"]},"syntology":{"n_ran":11,"n_constructed":0,"n_ran_checked":10,"n_instrument":1,"n_unverified":2,"n_samples":13,"n_pointer_only_licence":2,"sample_list":"/paper/exploring-target-representations-for-masked#ran","syntology_url":"https://syntology.ai/paper/2209.03917","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.03917"}}}},{"rank_in_archive_order":60,"model":"PAA (ResNext-152-32x8d + DCN, multi-scale)","metrics":{"AP50":"71.6","AP75":"59.1","APL":"66.9","APM":"56.3","APS":"36.0","box mAP":"53.5"},"uses_additional_data":false,"paper_date":"2020-07-16","paper":"/paper/probabilistic-anchor-assignment-with-iou","paper_url":"https://arxiv.org/abs/2007.08103v2","paper_title":"Probabilistic Anchor Assignment with IoU Prediction for Object Detection","code":"https://github.com/open-mmlab/mmdetection","n_code_links":5,"official":null,"syntology":null},{"rank_in_archive_order":61,"model":"LSNet (Res2Net-101+ DCN, multi-scale)","metrics":{"AP50":"71.1","AP75":"59.2","APL":"65.8","APM":"56.4","APS":"35.2","box mAP":"53.5"},"uses_additional_data":false,"paper_date":"2021-04-11","paper":"/paper/location-sensitive-visual-recognition-with","paper_url":"https://arxiv.org/abs/2104.04899v1","paper_title":"Location-Sensitive Visual Recognition with Cross-IOU Loss","code":"https://github.com/Duankaiwen/LSNet","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":62,"model":"dBOT ViT-B","metrics":{"box mAP":"53.5"},"uses_additional_data":false,"paper_date":"2022-09-08","paper":"/paper/exploring-target-representations-for-masked","paper_url":"https://arxiv.org/abs/2209.03917v3","paper_title":"Exploring Target Representations for Masked Autoencoders","code":"https://github.com/liuxingbin/dbot","n_code_links":1,"official":{"repos":["liuxingbin/dbot"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":2,"ran_from_kinds":["official"]},"syntology":{"n_ran":11,"n_constructed":0,"n_ran_checked":10,"n_instrument":1,"n_unverified":2,"n_samples":13,"n_pointer_only_licence":2,"sample_list":"/paper/exploring-target-representations-for-masked#ran","syntology_url":"https://syntology.ai/paper/2209.03917","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.03917"}}}},{"rank_in_archive_order":63,"model":"ResNeSt-200 (multi-scale)","metrics":{"AP50":"72.0","AP75":"58.0","APL":"66.8","APM":"56.2","APS":"35.1","box mAP":"53.3"},"uses_additional_data":false,"paper_date":"2020-04-19","paper":"/paper/resnest-split-attention-networks","paper_url":"https://arxiv.org/abs/2004.08955v2","paper_title":"ResNeSt: Split-Attention Networks","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":36,"official":{"repos":["zhanghang1989/ResNeSt"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":28,"n_constructed":0,"n_ran_checked":21,"n_instrument":7,"n_unverified":20,"n_samples":48,"n_pointer_only_licence":23,"sample_list":"/paper/resnest-split-attention-networks#ran","syntology_url":"https://syntology.ai/paper/2004.08955","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.08955"}}}},{"rank_in_archive_order":64,"model":"Cascade Mask R-CNN (Triple-ResNeXt152, multi-scale)","metrics":{"AP50":"71.9","AP75":"58.5 ","APL":" 66.7","APM":" 55.8","APS":"35.5","box mAP":"53.3"},"uses_additional_data":false,"paper_date":"2019-09-09","paper":"/paper/cbnet-a-novel-composite-backbone-network","paper_url":"https://arxiv.org/abs/1909.03625v1","paper_title":"CBNet: A Novel Composite Backbone Network Architecture for Object Detection","code":"https://github.com/open-mmlab/mmdetection","n_code_links":6,"official":{"repos":["PKUbahuangliuhe/CBNet"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":2,"n_samples":4,"n_pointer_only_licence":1,"sample_list":"/paper/cbnet-a-novel-composite-backbone-network#ran","syntology_url":"https://syntology.ai/paper/1909.03625","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.03625"}}}},{"rank_in_archive_order":65,"model":"DetectoRS (ResNeXt-101-32x4d, single-scale)","metrics":{"AP50":"71.6","AP75":"58.5","APL":"66.9","APM":"56.5","APS":"33.9","box mAP":"53.3"},"uses_additional_data":false,"paper_date":"2020-06-03","paper":"/paper/detectors-detecting-objects-with-recursive-1","paper_url":"https://arxiv.org/abs/2006.02334v2","paper_title":"DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolution","code":"https://github.com/open-mmlab/mmdetection","n_code_links":6,"official":{"repos":["joe-siyuan-qiao/DetectoRS"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_samples":4,"n_pointer_only_licence":0,"sample_list":"/paper/detectors-detecting-objects-with-recursive-1#ran","syntology_url":"https://syntology.ai/paper/2006.02334","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.02334"}}}},{"rank_in_archive_order":66,"model":"GFLV2 (Res2Net-101, DCN, multiscale)","metrics":{"AP50":"70.9","AP75":"59.2","APL":"65.6","APM":"56.1","APS":"35.7","box mAP":"53.3"},"uses_additional_data":false,"paper_date":"2020-11-25","paper":"/paper/generalized-focal-loss-v2-learning-reliable","paper_url":"https://arxiv.org/abs/2011.12885v1","paper_title":"Generalized Focal Loss V2: Learning Reliable Localization Quality Estimation for Dense Object Detection","code":"https://github.com/PaddlePaddle/PaddleDetection","n_code_links":5,"official":null,"syntology":null},{"rank_in_archive_order":67,"model":"YOLOv7-X (114 fps)","metrics":{"box mAP":"53.1"},"uses_additional_data":true,"paper_date":"2022-07-06","paper":"/paper/yolov7-trainable-bag-of-freebies-sets-new","paper_url":"https://arxiv.org/abs/2207.02696v1","paper_title":"YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors","code":"https://github.com/pjreddie/darknet","n_code_links":21,"official":{"repos":["wongkinyiu/yolov7"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":10,"n_constructed":0,"n_ran_checked":8,"n_instrument":2,"n_unverified":1,"n_samples":11,"n_pointer_only_licence":5,"sample_list":"/paper/yolov7-trainable-bag-of-freebies-sets-new#ran","syntology_url":"https://syntology.ai/paper/2207.02696","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.02696"}}}},{"rank_in_archive_order":68,"model":"RelationNet++ (ResNeXt-64x4d-101-DCN)","metrics":{"box mAP":"52.7"},"uses_additional_data":false,"paper_date":"2020-10-29","paper":"/paper/relationnet-bridging-visual-representations","paper_url":"https://arxiv.org/abs/2010.15831v1","paper_title":"RelationNet++: Bridging Visual Representations for Object Detection via Transformer Decoder","code":"https://github.com/shinya7y/UniverseNet","n_code_links":4,"official":{"repos":["microsoft/RelationNet2"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]},"syntology":{"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_samples":5,"n_pointer_only_licence":0,"sample_list":"/paper/relationnet-bridging-visual-representations#ran","syntology_url":"https://syntology.ai/paper/2010.15831","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.15831"}}}},{"rank_in_archive_order":69,"model":"EfficientDet-D7 (1536)","metrics":{"AP50":"71.6","AP75":"56.9","box mAP":"52.6"},"uses_additional_data":true,"paper_date":"2019-11-20","paper":"/paper/efficientdet-scalable-and-efficient-object","paper_url":"https://arxiv.org/abs/1911.09070v7","paper_title":"EfficientDet: Scalable and Efficient Object Detection","code":"https://github.com/tensorflow/models/tree/master/research/object_detection","n_code_links":64,"official":{"repos":["google/automl"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":55,"n_constructed":1,"n_ran_checked":48,"n_instrument":7,"n_unverified":15,"n_samples":70,"n_pointer_only_licence":7,"sample_list":"/paper/efficientdet-scalable-and-efficient-object#ran","syntology_url":"https://syntology.ai/paper/1911.09070","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.09070"}}}},{"rank_in_archive_order":70,"model":"YOLOv4-P5 with TTA","metrics":{"AP50":"70.3","AP75":"58","box mAP":"52.5"},"uses_additional_data":false,"paper_date":"2020-11-16","paper":"/paper/scaled-yolov4-scaling-cross-stage-partial","paper_url":"https://arxiv.org/abs/2011.08036v2","paper_title":"Scaled-YOLOv4: Scaling Cross Stage Partial Network","code":"https://github.com/AlexeyAB/darknet","n_code_links":41,"official":{"repos":["WongKinYiu/ScaledYOLOv4"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]},"syntology":{"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1,"sample_list":"/paper/scaled-yolov4-scaling-cross-stage-partial#ran","syntology_url":"https://syntology.ai/paper/2011.08036","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2011.08036"}}}},{"rank_in_archive_order":71,"model":"Deformable DETR (ResNeXt-101+DCN)","metrics":{"AP50":"71.9","AP75":"58.1","APL":"65.6","APM":"54.4","APS":"34.4","Hardware Burden":"17G","Operations per network pass":"17.3G","box mAP":"52.3"},"uses_additional_data":false,"paper_date":"2020-10-08","paper":"/paper/deformable-detr-deformable-transformers-for-1","paper_url":"https://arxiv.org/abs/2010.04159v4","paper_title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","code":"https://github.com/PaddlePaddle/PaddleDetection","n_code_links":20,"official":{"repos":["fundamentalvision/Deformable-DETR"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":37,"n_constructed":9,"n_ran_checked":24,"n_instrument":13,"n_unverified":18,"n_samples":55,"n_pointer_only_licence":21,"sample_list":"/paper/deformable-detr-deformable-transformers-for-1#ran","syntology_url":"https://syntology.ai/paper/2010.04159","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.04159"}}}},{"rank_in_archive_order":72,"model":"GCNet (ResNeXt-101 + DCN + cascade + GC r4)","metrics":{"AP50":"70.9","AP75":"56.9","box mAP":"52.3"},"uses_additional_data":false,"paper_date":"2020-12-24","paper":"/paper/global-context-networks","paper_url":"https://arxiv.org/abs/2012.13375v1","paper_title":"Global Context Networks","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":3,"official":null,"syntology":null},{"rank_in_archive_order":73,"model":"PP-YOLOE-x(CSPRepResNet-x, 640x640, single-scale )","metrics":{"AP50":"69.9","AP75":"56.5","APL":"66.4","APM":"56.3","APS":"33.3","box mAP":"52.2"},"uses_additional_data":false,"paper_date":"2022-03-30","paper":"/paper/pp-yoloe-an-evolved-version-of-yolo","paper_url":"https://arxiv.org/abs/2203.16250v3","paper_title":"PP-YOLOE: An evolved version of YOLO","code":"https://github.com/PaddlePaddle/PaddleDetection","n_code_links":8,"official":{"repos":["PaddlePaddle/PaddleDetection"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":22,"n_constructed":0,"n_ran_checked":19,"n_instrument":3,"n_unverified":5,"n_samples":27,"n_pointer_only_licence":1,"sample_list":"/paper/pp-yoloe-an-evolved-version-of-yolo#ran","syntology_url":"https://syntology.ai/paper/2203.16250","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.16250"}}}},{"rank_in_archive_order":74,"model":"RetinaNet (SpineNet-190, 1280x1280)","metrics":{"AP50":"71.8","AP75":"56.5","APL":"63.6","APM":"55","APS":"35.4","box mAP":"52.1"},"uses_additional_data":false,"paper_date":"2019-12-10","paper":"/paper/spinenet-learning-scale-permuted-backbone-for","paper_url":"https://arxiv.org/abs/1912.05027v3","paper_title":"SpineNet: Learning Scale-Permuted Backbone for Recognition and Localization","code":"https://github.com/tensorflow/models/tree/master/official/vision/beta/modeling/backbones","n_code_links":13,"official":null,"syntology":null},{"rank_in_archive_order":75,"model":"RepPoints v2 (ResNeXt-101, DCN, multi-scale)","metrics":{"AP50":"70.1","AP75":"57.5","APL":"63.6","APM":"54.6","APS":"34.5","box mAP":"52.1"},"uses_additional_data":false,"paper_date":"2020-07-16","paper":"/paper/reppoints-v2-verification-meets-regression","paper_url":"https://arxiv.org/abs/2007.08508v1","paper_title":"RepPoints V2: Verification Meets Regression for Object Detection","code":"https://github.com/Scalsol/RepPointsV2","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":76,"model":"AC-FPN Cascade R-CNN (X-152-32x8d-FPN-IN5k, multi scale, only CEM)","metrics":{"AP50":"70.4","AP75":"57","APL":"64.7","APM":"54.8","APS":"34.2","box mAP":"51.9"},"uses_additional_data":false,"paper_date":"2020-05-23","paper":"/paper/attention-guided-context-feature-pyramid","paper_url":"https://arxiv.org/abs/2005.11475v1","paper_title":"Attention-guided Context Feature Pyramid Network for Object Detection","code":"https://github.com/PaddlePaddle/PaddleDetection","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":77,"model":"OTA (ResNeXt-101+DCN, multiscale)","metrics":{"AP50":"68.6","AP75":"57.1","APL":"64.1","APM":"53.7","APS":"34.1","box mAP":"51.5"},"uses_additional_data":false,"paper_date":"2021-03-26","paper":"/paper/ota-optimal-transport-assignment-for-object","paper_url":"https://arxiv.org/abs/2103.14259v1","paper_title":"OTA: Optimal Transport Assignment for Object Detection","code":"https://github.com/Megvii-BaseDetection/OTA","n_code_links":2,"official":{"repos":["Megvii-BaseDetection/OTA"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":3,"n_constructed":1,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":2,"sample_list":"/paper/ota-optimal-transport-assignment-for-object#ran","syntology_url":"https://syntology.ai/paper/2103.14259","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.14259"}}}},{"rank_in_archive_order":78,"model":"YOLOX-x(Modified CSP v5, 640x640, single-scale)","metrics":{"box mAP":"51.5"},"uses_additional_data":true,"paper_date":"2021-07-18","paper":"/paper/yolox-exceeding-yolo-series-in-2021","paper_url":"https://arxiv.org/abs/2107.08430v2","paper_title":"YOLOX: Exceeding YOLO Series in 2021","code":"https://github.com/open-mmlab/mmdetection","n_code_links":42,"official":{"repos":["Megvii-BaseDetection/YOLOX"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":16,"n_constructed":0,"n_ran_checked":14,"n_instrument":2,"n_unverified":7,"n_samples":23,"n_pointer_only_licence":0,"sample_list":"/paper/yolox-exceeding-yolo-series-in-2021#ran","syntology_url":"https://syntology.ai/paper/2107.08430","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.08430"}}}},{"rank_in_archive_order":79,"model":"PP-YOLOE-l(CSPRepResNet-l, 640x640, single-scale )","metrics":{"AP50":"68.9","AP75":"55.6","APL":"66.1","APM":"55.3","APS":"31.4","box mAP":"51.4"},"uses_additional_data":false,"paper_date":"2022-03-30","paper":"/paper/pp-yoloe-an-evolved-version-of-yolo","paper_url":"https://arxiv.org/abs/2203.16250v3","paper_title":"PP-YOLOE: An evolved version of YOLO","code":"https://github.com/PaddlePaddle/PaddleDetection","n_code_links":8,"official":{"repos":["PaddlePaddle/PaddleDetection"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":22,"n_constructed":0,"n_ran_checked":19,"n_instrument":3,"n_unverified":5,"n_samples":27,"n_pointer_only_licence":1,"sample_list":"/paper/pp-yoloe-an-evolved-version-of-yolo#ran","syntology_url":"https://syntology.ai/paper/2203.16250","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.16250"}}}},{"rank_in_archive_order":80,"model":"YOLOv7 (161 fps)","metrics":{"box mAP":"51.4"},"uses_additional_data":true,"paper_date":"2022-07-06","paper":"/paper/yolov7-trainable-bag-of-freebies-sets-new","paper_url":"https://arxiv.org/abs/2207.02696v1","paper_title":"YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors","code":"https://github.com/pjreddie/darknet","n_code_links":21,"official":{"repos":["wongkinyiu/yolov7"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":10,"n_constructed":0,"n_ran_checked":8,"n_instrument":2,"n_unverified":1,"n_samples":11,"n_pointer_only_licence":5,"sample_list":"/paper/yolov7-trainable-bag-of-freebies-sets-new#ran","syntology_url":"https://syntology.ai/paper/2207.02696","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.02696"}}}},{"rank_in_archive_order":81,"model":"UniverseNet-20.08d (Res2Net-101, DCN, single-scale)","metrics":{"AP50":"70.0","AP75":"55.8","APL":"64.9","APM":"55.3","APS":"31.7","box mAP":"51.3"},"uses_additional_data":false,"paper_date":"2021-03-25","paper":"/paper/usb-universal-scale-object-detection","paper_url":"https://arxiv.org/abs/2103.14027v3","paper_title":"USB: Universal-Scale Object Detection Benchmark","code":"https://github.com/shinya7y/UniverseNet","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":82,"model":"TSD(SENet154-DCN,multi-scale)","metrics":{"AP50":"71.9","AP75":"56.0","APL":"64.2","APM":"54.8","APS":"33.8","box mAP":"51.2"},"uses_additional_data":false,"paper_date":"2020-03-17","paper":"/paper/revisiting-the-sibling-head-in-object","paper_url":"https://arxiv.org/abs/2003.07540v1","paper_title":"Revisiting the Sibling Head in Object Detector","code":"https://github.com/Sense-X/TSD","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":83,"model":"YOLOX-X (Modified CSP v5)","metrics":{"AP50":"69.6","AP75":"55.7","APL":"66.1","APM":"56.1","APS":"31.2","Params (M)":"99.1","box mAP":"51.2"},"uses_additional_data":false,"paper_date":"2021-07-18","paper":"/paper/yolox-exceeding-yolo-series-in-2021","paper_url":"https://arxiv.org/abs/2107.08430v2","paper_title":"YOLOX: Exceeding YOLO Series in 2021","code":"https://github.com/open-mmlab/mmdetection","n_code_links":42,"official":{"repos":["Megvii-BaseDetection/YOLOX"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":16,"n_constructed":0,"n_ran_checked":14,"n_instrument":2,"n_unverified":7,"n_samples":23,"n_pointer_only_licence":0,"sample_list":"/paper/yolox-exceeding-yolo-series-in-2021#ran","syntology_url":"https://syntology.ai/paper/2107.08430","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.08430"}}}},{"rank_in_archive_order":84,"model":"iBOT (ViT-B/16)","metrics":{"box mAP":"51.2"},"uses_additional_data":false,"paper_date":"2021-11-15","paper":"/paper/ibot-image-bert-pre-training-with-online","paper_url":"https://arxiv.org/abs/2111.07832v3","paper_title":"iBOT: Image BERT Pre-Training with Online Tokenizer","code":"https://github.com/bytedance/ibot","n_code_links":2,"official":{"repos":["bytedance/ibot"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]},"syntology":{"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0,"sample_list":"/paper/ibot-image-bert-pre-training-with-online#ran","syntology_url":"https://syntology.ai/paper/2111.07832","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.07832"}}}},{"rank_in_archive_order":85,"model":"RetinaNet (SpineNet-143, 1280x1280)","metrics":{"AP50":"70.4","AP75":"54.9","APL":"62.1","APM":"53.9","APS":"33.6","box mAP":"50.7"},"uses_additional_data":false,"paper_date":"2019-12-10","paper":"/paper/spinenet-learning-scale-permuted-backbone-for","paper_url":"https://arxiv.org/abs/1912.05027v3","paper_title":"SpineNet: Learning Scale-Permuted Backbone for Recognition and Localization","code":"https://github.com/tensorflow/models/tree/master/official/vision/beta/modeling/backbones","n_code_links":13,"official":null,"syntology":null},{"rank_in_archive_order":86,"model":"ATSS (ResNetXt-64x4d-101+DCN,multi-scale)","metrics":{"AP50":"68.9","AP75":"56.3","APL":"62.4","APM":"52.9","APS":"33.2","box mAP":"50.7"},"uses_additional_data":false,"paper_date":"2019-12-05","paper":"/paper/bridging-the-gap-between-anchor-based-and","paper_url":"https://arxiv.org/abs/1912.02424v4","paper_title":"Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection","code":"https://github.com/open-mmlab/mmdetection","n_code_links":13,"official":{"repos":["sfzhang15/ATSS"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_samples":4,"n_pointer_only_licence":0,"sample_list":"/paper/bridging-the-gap-between-anchor-based-and#ran","syntology_url":"https://syntology.ai/paper/1912.02424","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.02424"}}}},{"rank_in_archive_order":87,"model":"NAS-FPN (AmoebaNet-D, learned aug)","metrics":{"APL":"64.5","APM":"55.5","APS":"34.2","box mAP":"50.7"},"uses_additional_data":false,"paper_date":"2019-06-26","paper":"/paper/learning-data-augmentation-strategies-for","paper_url":"https://arxiv.org/abs/1906.11172v1","paper_title":"Learning Data Augmentation Strategies for Object Detection","code":"https://github.com/tensorflow/tpu","n_code_links":6,"official":{"repos":["tensorflow/tpu"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":3,"sample_list":"/paper/learning-data-augmentation-strategies-for#ran","syntology_url":"https://syntology.ai/paper/1906.11172","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.11172"}}}},{"rank_in_archive_order":88,"model":"Boosting R-CNN*","metrics":{"box mAP":"50.7"},"uses_additional_data":false,"paper_date":"2022-06-28","paper":"/paper/boosting-r-cnn-reweighting-r-cnn-samples-by","paper_url":"https://arxiv.org/abs/2206.13728v3","paper_title":"Boosting R-CNN: Reweighting R-CNN Samples by RPN's Error for Underwater Object Detection","code":"https://github.com/mousecpn/Boosting-R-CNN-Reweighting-R-CNN-Samples-by-RPN-s-Error-for-Underwater-Object-Detection","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":89,"model":"GFLV2 (Res2Net-101, DCN)","metrics":{"AP50":"69","AP75":"55.3","APL":"63.5","APM":"54.3","APS":"31.3","box mAP":"50.6"},"uses_additional_data":false,"paper_date":"2020-11-25","paper":"/paper/generalized-focal-loss-v2-learning-reliable","paper_url":"https://arxiv.org/abs/2011.12885v1","paper_title":"Generalized Focal Loss V2: Learning Reliable Localization Quality Estimation for Dense Object Detection","code":"https://github.com/PaddlePaddle/PaddleDetection","n_code_links":5,"official":null,"syntology":null},{"rank_in_archive_order":90,"model":"aLRP Loss (ResNext-101-64x4d, DCN, multiscale test)","metrics":{"AP50":"70.3","AP75":"53.9","APL":"63.0","APM":"53.1","APS":"32.0","box mAP":"50.2"},"uses_additional_data":false,"paper_date":"2020-09-28","paper":"/paper/a-ranking-based-balanced-loss-function","paper_url":"https://arxiv.org/abs/2009.13592v4","paper_title":"A Ranking-based, Balanced Loss Function Unifying Classification and Localisation in Object Detection","code":"https://github.com/kemaloksuz/aLRPLoss","n_code_links":3,"official":{"repos":["kemaloksuz/aLRPLoss"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":1,"sample_list":"/paper/a-ranking-based-balanced-loss-function#ran","syntology_url":"https://syntology.ai/paper/2009.13592","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2009.13592"}}}},{"rank_in_archive_order":91,"model":"FreeAnchor + SEPC (DCN, ResNext-101-64x4d)","metrics":{"AP50":"69.8","AP75":"54.3","APL":"63.7","APM":"53.3","APS":"31.3","box mAP":"50.1"},"uses_additional_data":false,"paper_date":"2020-05-06","paper":"/paper/scale-equalizing-pyramid-convolution-for","paper_url":"https://arxiv.org/abs/2005.03101v1","paper_title":"Scale-Equalizing Pyramid Convolution for Object Detection","code":"https://github.com/shinya7y/UniverseNet","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":92,"model":"D2Det (ResNet-101-DCN, multi-scale test)","metrics":{"AP50":"69.4","AP75":"54.9","APL":"62.1","APM":"52.7","APS":"32.7","box mAP":"50.1"},"uses_additional_data":false,"paper_date":"2020-06-01","paper":"/paper/d2det-towards-high-quality-object-detection","paper_url":"http://openaccess.thecvf.com/content_CVPR_2020/html/Cao_D2Det_Towards_High_Quality_Object_Detection_and_Instance_Segmentation_CVPR_2020_paper.html","paper_title":"D2Det: Towards High Quality Object Detection and Instance Segmentation","code":"https://github.com/JialeCao001/D2Det","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":93,"model":"Dynamic R-CNN (ResNet-101-DCN, multi-scale)","metrics":{"AP50":"68.3","AP75":"55.6","APL":"61.2","APM":"53.0","APS":"32.8","box mAP":"50.1"},"uses_additional_data":false,"paper_date":"2020-04-13","paper":"/paper/dynamic-r-cnn-towards-high-quality-object","paper_url":"https://arxiv.org/abs/2004.06002v2","paper_title":"Dynamic R-CNN: Towards High Quality Object Detection via Dynamic Training","code":"https://github.com/open-mmlab/mmdetection","n_code_links":3,"official":{"repos":["hkzhang95/DynamicRCNN"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":9,"n_samples":18,"n_pointer_only_licence":1,"sample_list":"/paper/dynamic-r-cnn-towards-high-quality-object#ran","syntology_url":"https://syntology.ai/paper/2004.06002","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.06002"}}}},{"rank_in_archive_order":94,"model":"TSD(ResNet-101-Deformable, Image Pyramid)","metrics":{"AP50":"69.6","AP75":"54.4","APL":"61.0","APM":"52.5","APS":"32.7","box mAP":"49.4"},"uses_additional_data":false,"paper_date":"2020-03-17","paper":"/paper/revisiting-the-sibling-head-in-object","paper_url":"https://arxiv.org/abs/2003.07540v1","paper_title":"Revisiting the Sibling Head in Object Detector","code":"https://github.com/Sense-X/TSD","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":95,"model":"RepPoints v2 (ResNeXt-101, DCN)","metrics":{"AP50":"68.9","AP75":"53.4","APL":"62.3","APM":"52.1","APS":"30.3","box mAP":"49.4"},"uses_additional_data":false,"paper_date":"2020-07-16","paper":"/paper/reppoints-v2-verification-meets-regression","paper_url":"https://arxiv.org/abs/2007.08508v1","paper_title":"RepPoints V2: Verification Meets Regression for Object Detection","code":"https://github.com/Scalsol/RepPointsV2","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":96,"model":"A2MIM (ViT-B)","metrics":{"box mAP":"49.4"},"uses_additional_data":false,"paper_date":"2022-05-27","paper":"/paper/architecture-agnostic-masked-image-modeling","paper_url":"https://arxiv.org/abs/2205.13943v4","paper_title":"Architecture-Agnostic Masked Image Modeling -- From ViT back to CNN","code":"https://github.com/open-mmlab/mmpretrain","n_code_links":3,"official":null,"syntology":null},{"rank_in_archive_order":97,"model":"iBOT (ViT-S/16)","metrics":{"box mAP":"49.4"},"uses_additional_data":false,"paper_date":"2021-11-15","paper":"/paper/ibot-image-bert-pre-training-with-online","paper_url":"https://arxiv.org/abs/2111.07832v3","paper_title":"iBOT: Image BERT Pre-Training with Online Tokenizer","code":"https://github.com/bytedance/ibot","n_code_links":2,"official":{"repos":["bytedance/ibot"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]},"syntology":{"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0,"sample_list":"/paper/ibot-image-bert-pre-training-with-online#ran","syntology_url":"https://syntology.ai/paper/2111.07832","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.07832"}}}},{"rank_in_archive_order":98,"model":"CPNDet (Hourglass-104, multi-scale)","metrics":{"AP50":"67.3","AP75":"53.7","APL":"62.4","APM":"51.9","APS":"31.0","box mAP":"49.2"},"uses_additional_data":false,"paper_date":"2020-07-27","paper":"/paper/corner-proposal-network-for-anchor-free-two","paper_url":"https://arxiv.org/abs/2007.13816v1","paper_title":"Corner Proposal Network for Anchor-free, Two-stage Object Detection","code":"https://github.com/Duankaiwen/CPNDet","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":99,"model":"GFLV2 (ResNeXt-101, 32x4d, DCN)","metrics":{"AP50":"67.6","AP75":"53.5","APL":"61.4","APM":"52.4","APS":"29.7","Hardware Burden":"3G","box mAP":"49"},"uses_additional_data":false,"paper_date":"2020-11-25","paper":"/paper/generalized-focal-loss-v2-learning-reliable","paper_url":"https://arxiv.org/abs/2011.12885v1","paper_title":"Generalized Focal Loss V2: Learning Reliable Localization Quality Estimation for Dense Object Detection","code":"https://github.com/PaddlePaddle/PaddleDetection","n_code_links":5,"official":null,"syntology":null},{"rank_in_archive_order":100,"model":"aLRP Loss (ResNext-101-64x4d, DCN, single scale)","metrics":{"AP50":"69.3","AP75":"52.5","APL":"62.1","APM":"51.5","APS":"30.8","box mAP":"48.9"},"uses_additional_data":false,"paper_date":"2020-09-28","paper":"/paper/a-ranking-based-balanced-loss-function","paper_url":"https://arxiv.org/abs/2009.13592v4","paper_title":"A Ranking-based, Balanced Loss Function Unifying Classification and Localisation in Object Detection","code":"https://github.com/kemaloksuz/aLRPLoss","n_code_links":3,"official":{"repos":["kemaloksuz/aLRPLoss"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":1,"sample_list":"/paper/a-ranking-based-balanced-loss-function#ran","syntology_url":"https://syntology.ai/paper/2009.13592","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2009.13592"}}}},{"rank_in_archive_order":101,"model":"PP-YOLOE-m(CSPRepResNet-m, 640x640, single-scale )","metrics":{"AP50":"66.5","AP75":"53.0","APL":"63.8","APM":"52.9","APS":"28.6","box mAP":"48.9"},"uses_additional_data":false,"paper_date":"2022-03-30","paper":"/paper/pp-yoloe-an-evolved-version-of-yolo","paper_url":"https://arxiv.org/abs/2203.16250v3","paper_title":"PP-YOLOE: An evolved version of YOLO","code":"https://github.com/PaddlePaddle/PaddleDetection","n_code_links":8,"official":{"repos":["PaddlePaddle/PaddleDetection"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":22,"n_constructed":0,"n_ran_checked":19,"n_instrument":3,"n_unverified":5,"n_samples":27,"n_pointer_only_licence":1,"sample_list":"/paper/pp-yoloe-an-evolved-version-of-yolo#ran","syntology_url":"https://syntology.ai/paper/2203.16250","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.16250"}}}},{"rank_in_archive_order":102,"model":"UniverseNet-20.08 (Res2Net-50, DCN, single-scale)","metrics":{"AP50":"67.5","AP75":"53.0","APL":"61.1","APM":"52.3","APS":"30.1","box mAP":"48.8"},"uses_additional_data":false,"paper_date":"2021-03-25","paper":"/paper/usb-universal-scale-object-detection","paper_url":"https://arxiv.org/abs/2103.14027v3","paper_title":"USB: Universal-Scale Object Detection Benchmark","code":"https://github.com/shinya7y/UniverseNet","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":103,"model":"SOLQ (ResNet101, single scale)","metrics":{"box mAP":"48.7"},"uses_additional_data":false,"paper_date":"2021-06-04","paper":"/paper/solq-segmenting-objects-by-learning-queries","paper_url":"https://arxiv.org/abs/2106.02351v3","paper_title":"SOLQ: Segmenting Objects by Learning Queries","code":"https://github.com/megvii-research/SOLQ","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":104,"model":"RetinaNet (SpineNet-96, 1024x1024)","metrics":{"AP50":"68.4","AP75":"52.5","APL":"62","APM":"52.3","APS":"32","box mAP":"48.6"},"uses_additional_data":false,"paper_date":"2019-12-10","paper":"/paper/spinenet-learning-scale-permuted-backbone-for","paper_url":"https://arxiv.org/abs/1912.05027v3","paper_title":"SpineNet: Learning Scale-Permuted Backbone for Recognition and Localization","code":"https://github.com/tensorflow/models/tree/master/official/vision/beta/modeling/backbones","n_code_links":13,"official":null,"syntology":null},{"rank_in_archive_order":105,"model":"TridentNet (ResNet-101-Deformable, Image Pyramid)","metrics":{"AP50":"69.7","AP75":"53.5","APL":"60.3","APM":"51.3","APS":"31.8","box mAP":"48.4"},"uses_additional_data":false,"paper_date":"2019-01-07","paper":"/paper/scale-aware-trident-networks-for-object","paper_url":"https://arxiv.org/abs/1901.01892v2","paper_title":"Scale-Aware Trident Networks for Object Detection","code":"https://github.com/facebookresearch/detectron2/tree/master/projects/TridentNet/","n_code_links":4,"official":null,"syntology":null},{"rank_in_archive_order":106,"model":"GCNet (ResNeXt-101 + DCN + cascade + GC r4)","metrics":{"AP50":"67.6","AP75":"52.7","Operations per network pass":"54.8G","box mAP":"48.4"},"uses_additional_data":false,"paper_date":"2019-04-25","paper":"/paper/gcnet-non-local-networks-meet-squeeze","paper_url":"http://arxiv.org/abs/1904.11492v1","paper_title":"GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond","code":"https://github.com/open-mmlab/mmdetection","n_code_links":9,"official":null,"syntology":null},{"rank_in_archive_order":107,"model":"GFLV2 (ResNet-101-DCN)","metrics":{"AP50":"66.5","AP75":"52.8","APL":"60.7","APM":"51.9","APS":"28.8","Hardware Burden":"3G","box mAP":"48.3"},"uses_additional_data":false,"paper_date":"2020-11-25","paper":"/paper/generalized-focal-loss-v2-learning-reliable","paper_url":"https://arxiv.org/abs/2011.12885v1","paper_title":"Generalized Focal Loss V2: Learning Reliable Localization Quality Estimation for Dense Object Detection","code":"https://github.com/PaddlePaddle/PaddleDetection","n_code_links":5,"official":null,"syntology":null},{"rank_in_archive_order":108,"model":"Swin-S (RPE w/ GAB)","metrics":{"box mAP":"48.23"},"uses_additional_data":false,"paper_date":"2023-05-08","paper":"/paper/understanding-gaussian-attention-bias-of","paper_url":"https://arxiv.org/abs/2305.04722v1","paper_title":"Understanding Gaussian Attention Bias of Vision Transformers Using Effective Receptive Fields","code":"https://github.com/kmbmjn/GaussianAttentionBias","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":109,"model":"GFL (X-101-32x4d-DCN, single-scale)","metrics":{"AP50":"67.4","AP75":"52.6","APL":"60.2","APM":"51.7","APS":"29.2","box mAP":"48.2"},"uses_additional_data":false,"paper_date":"2020-06-08","paper":"/paper/generalized-focal-loss-learning-qualified-and","paper_url":"https://arxiv.org/abs/2006.04388v1","paper_title":"Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection","code":"https://github.com/open-mmlab/mmdetection","n_code_links":7,"official":{"repos":["implus/GFocal"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":22,"n_constructed":0,"n_ran_checked":21,"n_instrument":1,"n_unverified":2,"n_samples":24,"n_pointer_only_licence":2,"sample_list":"/paper/generalized-focal-loss-learning-qualified-and#ran","syntology_url":"https://syntology.ai/paper/2006.04388","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.04388"}}}},{"rank_in_archive_order":110,"model":"ISTR (ResNet101-FPN-3x, single-scale)","metrics":{"APL":"61.5","APM":"50.4","APS":"28.7","box mAP":"48.1"},"uses_additional_data":false,"paper_date":"2021-05-03","paper":"/paper/istr-end-to-end-instance-segmentation-with","paper_url":"https://arxiv.org/abs/2105.00637v2","paper_title":"ISTR: End-to-End Instance Segmentation with Transformers","code":"https://github.com/hujiecpp/ISTR","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":111,"model":"YOLOX-Darknet53(Darknet53, 640x640, single-scale)","metrics":{"box mAP":"48.0"},"uses_additional_data":true,"paper_date":"2021-07-18","paper":"/paper/yolox-exceeding-yolo-series-in-2021","paper_url":"https://arxiv.org/abs/2107.08430v2","paper_title":"YOLOX: Exceeding YOLO Series in 2021","code":"https://github.com/open-mmlab/mmdetection","n_code_links":42,"official":{"repos":["Megvii-BaseDetection/YOLOX"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":16,"n_constructed":0,"n_ran_checked":14,"n_instrument":2,"n_unverified":7,"n_samples":23,"n_pointer_only_licence":0,"sample_list":"/paper/yolox-exceeding-yolo-series-in-2021#ran","syntology_url":"https://syntology.ai/paper/2107.08430","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.08430"}}}},{"rank_in_archive_order":112,"model":"DAT-S (RetinaNet)","metrics":{"AP50":"69.6","AP75":"51.2","APL":"63.4","APM":"51.8","APS":"32.3","box mAP":"47.9"},"uses_additional_data":false,"paper_date":"2022-01-03","paper":"/paper/vision-transformer-with-deformable-attention","paper_url":"https://arxiv.org/abs/2201.00520v3","paper_title":"Vision Transformer with Deformable Attention","code":"https://github.com/leaplabthu/dat","n_code_links":2,"official":{"repos":["leaplabthu/dat"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":8,"n_constructed":4,"n_ran_checked":4,"n_instrument":4,"n_unverified":2,"n_samples":10,"n_pointer_only_licence":0,"sample_list":"/paper/vision-transformer-with-deformable-attention#ran","syntology_url":"https://syntology.ai/paper/2201.00520","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.00520"}}}},{"rank_in_archive_order":113,"model":"aLRP Loss (ResNext-101-64x4d, single scale)","metrics":{"AP50":"68.4","AP75":"51.1","APL":"59.1","APM":"50.8","APS":"30.2","box mAP":"47.8"},"uses_additional_data":false,"paper_date":"2020-09-28","paper":"/paper/a-ranking-based-balanced-loss-function","paper_url":"https://arxiv.org/abs/2009.13592v4","paper_title":"A Ranking-based, Balanced Loss Function Unifying Classification and Localisation in Object Detection","code":"https://github.com/kemaloksuz/aLRPLoss","n_code_links":3,"official":{"repos":["kemaloksuz/aLRPLoss"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":1,"sample_list":"/paper/a-ranking-based-balanced-loss-function#ran","syntology_url":"https://syntology.ai/paper/2009.13592","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2009.13592"}}}},{"rank_in_archive_order":114,"model":"MatrixNet Corners (ResNet-152, multi-scale)","metrics":{"AP50":"66.2","AP75":"52.3","APL":"60.7","APM":"50.4","APS":"29.7","box mAP":"47.8"},"uses_additional_data":false,"paper_date":"2019-08-13","paper":"/paper/matrix-nets-a-new-deep-architecture-for","paper_url":"https://arxiv.org/abs/1908.04646v2","paper_title":"Matrix Nets: A New Deep Architecture for Object Detection","code":"https://github.com/arashwan/matrixnet","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":115,"model":"SOLQ (ResNet50, single scale)","metrics":{"box mAP":"47.8"},"uses_additional_data":false,"paper_date":"2021-06-04","paper":"/paper/solq-segmenting-objects-by-learning-queries","paper_url":"https://arxiv.org/abs/2106.02351v3","paper_title":"SOLQ: Segmenting Objects by Learning Queries","code":"https://github.com/megvii-research/SOLQ","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":116,"model":"DyHead (ResNeXt-64x4d-101)","metrics":{"AP50":"65.7","AP75":"51.9","box mAP":"47.7"},"uses_additional_data":false,"paper_date":"2021-06-15","paper":"/paper/dynamic-head-unifying-object-detection-heads","paper_url":"https://arxiv.org/abs/2106.08322v1","paper_title":"Dynamic Head: Unifying Object Detection Heads with Attentions","code":"https://github.com/open-mmlab/mmdetection","n_code_links":3,"official":{"repos":["microsoft/DynamicHead"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":8,"n_constructed":5,"n_ran_checked":6,"n_instrument":2,"n_unverified":1,"n_samples":9,"n_pointer_only_licence":0,"sample_list":"/paper/dynamic-head-unifying-object-detection-heads#ran","syntology_url":"https://syntology.ai/paper/2106.08322","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.08322"}}}},{"rank_in_archive_order":117,"model":"SAPD (ResNeXt-101, single-scale)","metrics":{"AP50":"67.4","AP75":"51.1","APL":"61.5","APM":"50.3","APS":"28.1","box mAP":"47.4"},"uses_additional_data":false,"paper_date":"2019-11-27","paper":"/paper/soft-anchor-point-object-detection","paper_url":"https://arxiv.org/abs/1911.12448v2","paper_title":"Soft Anchor-Point Object Detection","code":"https://github.com/xuannianz/FSAF","n_code_links":2,"official":null,"syntology":{"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":2,"n_samples":6,"n_pointer_only_licence":0,"sample_list":"/paper/soft-anchor-point-object-detection#ran","syntology_url":"https://syntology.ai/paper/1911.12448","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.12448"}}}},{"rank_in_archive_order":118,"model":"PANet (ResNeXt-101, multi-scale)","metrics":{"AP50":"67.2","AP75":"51.8 ","APL":"60.0 ","APM":"51.7","APS":"30.1","box mAP":"47.4"},"uses_additional_data":false,"paper_date":"2018-03-05","paper":"/paper/path-aggregation-network-for-instance","paper_url":"http://arxiv.org/abs/1803.01534v4","paper_title":"Path Aggregation Network for Instance Segmentation","code":"https://github.com/ultralytics/yolov5","n_code_links":10,"official":{"repos":["ShuLiu1993/PANet"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official","unlocated"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":1,"n_samples":4,"n_pointer_only_licence":2,"sample_list":"/paper/path-aggregation-network-for-instance#ran","syntology_url":"https://syntology.ai/paper/1803.01534","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1803.01534"}}}},{"rank_in_archive_order":119,"model":"HTC (HRNetV2p-W48)","metrics":{"AP50":"65.9","AP75":"51.2","APL":"59.8","APM":"49.7","APS":"28.0","Hardware Burden":"15G","Operations per network pass":"71.7G","box mAP":"47.3"},"uses_additional_data":false,"paper_date":"2019-08-20","paper":"/paper/190807919","paper_url":"https://arxiv.org/abs/1908.07919v2","paper_title":"Deep High-Resolution Representation Learning for Visual Recognition","code":"https://github.com/open-mmlab/mmdetection","n_code_links":42,"official":null,"syntology":{"n_ran":21,"n_constructed":0,"n_ran_checked":16,"n_instrument":5,"n_unverified":13,"n_samples":34,"n_pointer_only_licence":21,"sample_list":"/paper/190807919#ran","syntology_url":"https://syntology.ai/paper/1908.07919","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.07919"}}}},{"rank_in_archive_order":120,"model":"HTC (ResNeXt-101-FPN)","metrics":{"AP50":"63.9","AP75":"44.7","APL":"54.6","APM":"43.9","APS":"22.8","box mAP":"47.1"},"uses_additional_data":false,"paper_date":"2019-01-22","paper":"/paper/hybrid-task-cascade-for-instance-segmentation","paper_url":"http://arxiv.org/abs/1901.07518v2","paper_title":"Hybrid Task Cascade for Instance Segmentation","code":"https://github.com/open-mmlab/mmdetection","n_code_links":5,"official":{"repos":["open-mmlab/mmdetection"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":0,"n_samples":11,"n_pointer_only_licence":0,"sample_list":"/paper/hybrid-task-cascade-for-instance-segmentation#ran","syntology_url":"https://syntology.ai/paper/1901.07518","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.07518"}}}},{"rank_in_archive_order":121,"model":"CenterNet511 (Hourglass-104, multi-scale)","metrics":{"AP50":"64.5","AP75":"50.7","APL":"58.9","APM":"49.9","APS":"28.9","box mAP":"47.0"},"uses_additional_data":false,"paper_date":"2019-04-17","paper":"/paper/centernet-object-detection-with-keypoint","paper_url":"http://arxiv.org/abs/1904.08189v3","paper_title":"CenterNet: Keypoint Triplets for Object Detection","code":"https://github.com/Duankaiwen/CenterNet","n_code_links":20,"official":{"repos":["Duankaiwen/CenterNet"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["listed"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":9,"n_samples":11,"n_pointer_only_licence":4,"sample_list":"/paper/centernet-object-detection-with-keypoint#ran","syntology_url":"https://syntology.ai/paper/1904.08189","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.08189"}}}},{"rank_in_archive_order":122,"model":"MAL (ResNeXt101, multi-scale)","metrics":{"box mAP":"47.0"},"uses_additional_data":false,"paper_date":"2019-12-04","paper":"/paper/multiple-anchor-learning-for-visual-object","paper_url":"https://arxiv.org/abs/1912.02252v1","paper_title":"Multiple Anchor Learning for Visual Object Detection","code":"https://github.com/KevinKecc/MAL","n_code_links":3,"official":null,"syntology":{"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":3,"n_samples":10,"n_pointer_only_licence":1,"sample_list":"/paper/multiple-anchor-learning-for-visual-object#ran","syntology_url":"https://syntology.ai/paper/1912.02252","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.02252"}}}},{"rank_in_archive_order":123,"model":"ISTR (ResNet50-FPN-3x)","metrics":{"box mAP":"46.8"},"uses_additional_data":false,"paper_date":"2021-05-03","paper":"/paper/istr-end-to-end-instance-segmentation-with","paper_url":"https://arxiv.org/abs/2105.00637v2","paper_title":"ISTR: End-to-End Instance Segmentation with Transformers","code":"https://github.com/hujiecpp/ISTR","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":124,"model":"RetinaNet (SpineNet-49, 896x896)","metrics":{"AP50":"66.3","AP75":"50.6","APL":"61.7","APM":"50.1","APS":"29.1","box mAP":"46.7"},"uses_additional_data":false,"paper_date":"2019-12-10","paper":"/paper/spinenet-learning-scale-permuted-backbone-for","paper_url":"https://arxiv.org/abs/1912.05027v3","paper_title":"SpineNet: Learning Scale-Permuted Backbone for Recognition and Localization","code":"https://github.com/tensorflow/models/tree/master/official/vision/beta/modeling/backbones","n_code_links":13,"official":null,"syntology":null},{"rank_in_archive_order":125,"model":"RPDet (ResNet-101-DCN, multi-scale)","metrics":{"AP50":"67.4","AP75":"50.9","APL":"57.1","APM":"49.7","APS":"30.3","box mAP":"46.5"},"uses_additional_data":false,"paper_date":"2019-04-25","paper":"/paper/reppoints-point-set-representation-for-object","paper_url":"https://arxiv.org/abs/1904.11490v2","paper_title":"RepPoints: Point Set Representation for Object Detection","code":"https://github.com/open-mmlab/mmdetection","n_code_links":6,"official":{"repos":["microsoft/RepPoints"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":3,"sample_list":"/paper/reppoints-point-set-representation-for-object#ran","syntology_url":"https://syntology.ai/paper/1904.11490","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.11490"}}}},{"rank_in_archive_order":126,"model":"HoughNet (MS)","metrics":{"AP50":"65.1","AP75":"50.7","APL":"58.1","APM":"48.5","APS":"29.1","box mAP":"46.4"},"uses_additional_data":false,"paper_date":"2020-07-05","paper":"/paper/houghnet-integrating-near-and-long-range","paper_url":"https://arxiv.org/abs/2007.02355v3","paper_title":"HoughNet: Integrating near and long-range evidence for bottom-up object detection","code":"https://github.com/giddyyupp/coco-minitrain","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":127,"model":"PPDet (ResNeXt-101-FPN, multiscale)","metrics":{"AP50":"64.8","AP75":"51.6","APL":"56.4","APM":"49.9","APS":"31.4","box mAP":"46.3"},"uses_additional_data":false,"paper_date":"2020-08-03","paper":"/paper/reducing-label-noise-in-anchor-free-object","paper_url":"https://arxiv.org/abs/2008.01167v2","paper_title":"Reducing Label Noise in Anchor-Free Object Detection","code":"https://github.com/nerminsamet/ppdet","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":128,"model":"GFLV2 (ResNet-101)","metrics":{"AP50":"64.3","AP75":"50.5","APL":"57","APM":"49.9","APS":"27.8","box mAP":"46.2"},"uses_additional_data":false,"paper_date":"2020-11-25","paper":"/paper/generalized-focal-loss-v2-learning-reliable","paper_url":"https://arxiv.org/abs/2011.12885v1","paper_title":"Generalized Focal Loss V2: Learning Reliable Localization Quality Estimation for Dense Object Detection","code":"https://github.com/PaddlePaddle/PaddleDetection","n_code_links":5,"official":null,"syntology":null},{"rank_in_archive_order":129,"model":"SNIPER (ResNet-101)","metrics":{"AP50":"67.0","AP75":"51.6","APL":"58.1","APM":"48.9","APS":"29.6","Hardware Burden":"29G","box mAP":"46.1"},"uses_additional_data":false,"paper_date":"2018-05-23","paper":"/paper/sniper-efficient-multi-scale-training","paper_url":"http://arxiv.org/abs/1805.09300v3","paper_title":"SNIPER: Efficient Multi-Scale Training","code":"https://github.com/PaddlePaddle/PaddleDetection","n_code_links":4,"official":null,"syntology":null},{"rank_in_archive_order":130,"model":"Mask R-CNN (HRNetV2p-W48 + cascade)","metrics":{"AP50":"64.0","AP75":"50.3","APL":"58.3","APM":"48.6","APS":"27.1","Hardware Burden":"15G","Operations per network pass":"61.8G","box mAP":"46.1"},"uses_additional_data":false,"paper_date":"2019-08-20","paper":"/paper/190807919","paper_url":"https://arxiv.org/abs/1908.07919v2","paper_title":"Deep High-Resolution Representation Learning for Visual Recognition","code":"https://github.com/open-mmlab/mmdetection","n_code_links":42,"official":null,"syntology":{"n_ran":21,"n_constructed":0,"n_ran_checked":16,"n_instrument":5,"n_unverified":13,"n_samples":34,"n_pointer_only_licence":21,"sample_list":"/paper/190807919#ran","syntology_url":"https://syntology.ai/paper/1908.07919","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.07919"}}}},{"rank_in_archive_order":131,"model":"ResNeXt-64x4d-101 NAS-FCOS @128-256 w/improvements","metrics":{"box mAP":"46.1"},"uses_additional_data":false,"paper_date":"2019-06-11","paper":"/paper/nas-fcos-fast-neural-architecture-search-for","paper_url":"https://arxiv.org/abs/1906.04423v4","paper_title":"NAS-FCOS: Fast Neural Architecture Search for Object Detection","code":"https://github.com/open-mmlab/mmdetection","n_code_links":3,"official":null,"syntology":{"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":0,"n_samples":7,"n_pointer_only_licence":1,"sample_list":"/paper/nas-fcos-fast-neural-architecture-search-for#ran","syntology_url":"https://syntology.ai/paper/1906.04423","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.04423"}}}},{"rank_in_archive_order":132,"model":"DCNv2 (ResNet-101, multi-scale)","metrics":{"AP50":"67.9","AP75":"50.8","APL":"59.5","APM":"49.1","APS":"27.8","box mAP":"46.0"},"uses_additional_data":false,"paper_date":"2018-11-27","paper":"/paper/deformable-convnets-v2-more-deformable-better","paper_url":"http://arxiv.org/abs/1811.11168v2","paper_title":"Deformable ConvNets v2: More Deformable, Better Results","code":"https://github.com/open-mmlab/mmdetection","n_code_links":26,"official":null,"syntology":{"n_ran":10,"n_constructed":0,"n_ran_checked":9,"n_instrument":1,"n_unverified":3,"n_samples":13,"n_pointer_only_licence":4,"sample_list":"/paper/deformable-convnets-v2-more-deformable-better#ran","syntology_url":"https://syntology.ai/paper/1811.11168","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.11168"}}}},{"rank_in_archive_order":133,"model":"Gaussian-FCOS","metrics":{"box mAP":"46"},"uses_additional_data":false,"paper_date":"2020-06-28","paper":"/paper/localization-uncertainty-estimation-for","paper_url":"https://arxiv.org/abs/2006.15607v6","paper_title":"Localization Uncertainty Estimation for Anchor-Free Object Detection","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":134,"model":"Cascade R-CNN-FPN (ResNet-101, map-guided)","metrics":{"AP50":"64.2","AP75":"50","APL":"58.6","APM":"49","APS":"26.3","box mAP":"45.9"},"uses_additional_data":false,"paper_date":"2019-08-21","paper":"/paper/instaboost-boosting-instance-segmentation-via","paper_url":"https://arxiv.org/abs/1908.07801v1","paper_title":"InstaBoost: Boosting Instance Segmentation via Probability Map Guided Copy-Pasting","code":"https://github.com/open-mmlab/mmdetection","n_code_links":3,"official":null,"syntology":null},{"rank_in_archive_order":135,"model":"MAL (ResNeXt101, single-scale)","metrics":{"box mAP":"45.9"},"uses_additional_data":false,"paper_date":"2019-12-04","paper":"/paper/multiple-anchor-learning-for-visual-object","paper_url":"https://arxiv.org/abs/1912.02252v1","paper_title":"Multiple Anchor Learning for Visual Object Detection","code":"https://github.com/KevinKecc/MAL","n_code_links":3,"official":null,"syntology":{"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":3,"n_samples":10,"n_pointer_only_licence":1,"sample_list":"/paper/multiple-anchor-learning-for-visual-object#ran","syntology_url":"https://syntology.ai/paper/1912.02252","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.02252"}}}},{"rank_in_archive_order":136,"model":"CenterMask+VoVNetV2-99 (single-scale)","metrics":{"AP50":"64.5","APL":"57.6","APM":"48.3","APS":"27.8","box mAP":"45.8"},"uses_additional_data":false,"paper_date":"2019-11-15","paper":"/paper/centermask-real-time-anchor-free-instance-1","paper_url":"https://arxiv.org/abs/1911.06667v6","paper_title":"CenterMask : Real-Time Anchor-Free Instance Segmentation","code":"https://github.com/youngwanLEE/centermask2","n_code_links":8,"official":{"repos":["youngwanLEE/CenterMask"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2,"sample_list":"/paper/centermask-real-time-anchor-free-instance-1#ran","syntology_url":"https://syntology.ai/paper/1911.06667","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.06667"}}}},{"rank_in_archive_order":137,"model":"D-RFCN + SNIP (DPN-98 with flip, multi-scale)","metrics":{"AP50":"67.3","AP75":"51.1","APL":"57.1","APM":"48.8","APS":"29.3","box mAP":"45.7"},"uses_additional_data":false,"paper_date":"2017-11-22","paper":"/paper/an-analysis-of-scale-invariance-in-object-1","paper_url":"http://arxiv.org/abs/1711.08189v2","paper_title":"An Analysis of Scale Invariance in Object Detection - SNIP","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":138,"model":"YOLOv4 (CD53)","metrics":{"AP50":"64.1","AP75":"49.5","APL":"56.7","APM":"49","APS":"27","box mAP":"45.5"},"uses_additional_data":true,"paper_date":"2020-11-16","paper":"/paper/scaled-yolov4-scaling-cross-stage-partial","paper_url":"https://arxiv.org/abs/2011.08036v2","paper_title":"Scaled-YOLOv4: Scaling Cross Stage Partial Network","code":"https://github.com/AlexeyAB/darknet","n_code_links":41,"official":{"repos":["WongKinYiu/ScaledYOLOv4"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]},"syntology":{"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1,"sample_list":"/paper/scaled-yolov4-scaling-cross-stage-partial#ran","syntology_url":"https://syntology.ai/paper/2011.08036","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2011.08036"}}}},{"rank_in_archive_order":139,"model":"AC-FPN Cascade R-CNN(ResNet-101, single scale)","metrics":{"AP50":"64.4","AP75":"49","APL":"56.6","APM":"47.7","APS":"26.9","box mAP":"45"},"uses_additional_data":false,"paper_date":"2020-05-23","paper":"/paper/attention-guided-context-feature-pyramid","paper_url":"https://arxiv.org/abs/2005.11475v1","paper_title":"Attention-guided Context Feature Pyramid Network for Object Detection","code":"https://github.com/PaddlePaddle/PaddleDetection","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":140,"model":"FreeAnchor (ResNeXt-101)","metrics":{"AP50":"64.3","AP75":"48.4","APL":"56","APM":"47.9","APS":"27","box mAP":"44.8"},"uses_additional_data":false,"paper_date":"2019-09-05","paper":"/paper/freeanchor-learning-to-match-anchors-for","paper_url":"https://arxiv.org/abs/1909.02466v2","paper_title":"FreeAnchor: Learning to Match Anchors for Visual Object Detection","code":"https://github.com/open-mmlab/mmdetection","n_code_links":4,"official":{"repos":["zhangxiaosong18/FreeAnchor"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":0,"sample_list":"/paper/freeanchor-learning-to-match-anchors-for#ran","syntology_url":"https://syntology.ai/paper/1909.02466","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.02466"}}}},{"rank_in_archive_order":141,"model":"FCOS (ResNeXt-64x4d-101-FPN 4 + improvements)","metrics":{"AP50":"64.1","AP75":"48.4","APL":"55.6","APM":"47.5","APS":"27.6","box mAP":"44.7"},"uses_additional_data":false,"paper_date":"2019-04-02","paper":"/paper/fcos-fully-convolutional-one-stage-object","paper_url":"https://arxiv.org/abs/1904.01355v5","paper_title":"FCOS: Fully Convolutional One-Stage Object Detection","code":"https://github.com/open-mmlab/mmdetection","n_code_links":87,"official":{"repos":["tianzhi0549/FCOS"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]},"syntology":{"n_ran":37,"n_constructed":0,"n_ran_checked":30,"n_instrument":7,"n_unverified":3,"n_samples":40,"n_pointer_only_licence":19,"sample_list":"/paper/fcos-fully-convolutional-one-stage-object#ran","syntology_url":"https://syntology.ai/paper/1904.01355","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.01355"}}}},{"rank_in_archive_order":142,"model":"CenterMask+VoVNet2-57 (single-scale)","metrics":{"AP50":"63.1","AP75":"48.6","APL":"55.9","APS":"27.1","box mAP":"44.7"},"uses_additional_data":false,"paper_date":"2019-11-15","paper":"/paper/centermask-real-time-anchor-free-instance-1","paper_url":"https://arxiv.org/abs/1911.06667v6","paper_title":"CenterMask : Real-Time Anchor-Free Instance Segmentation","code":"https://github.com/youngwanLEE/centermask2","n_code_links":8,"official":{"repos":["youngwanLEE/CenterMask"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2,"sample_list":"/paper/centermask-real-time-anchor-free-instance-1#ran","syntology_url":"https://syntology.ai/paper/1911.06667","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.06667"}}}},{"rank_in_archive_order":143,"model":"FSAF (ResNeXt-101, multi-scale)","metrics":{"AP50":"65.2","AP75":"48.6","APL":"54.6","APM":"47.1","APS":"29.7","box mAP":"44.6"},"uses_additional_data":false,"paper_date":"2019-03-02","paper":"/paper/feature-selective-anchor-free-module-for","paper_url":"http://arxiv.org/abs/1903.00621v1","paper_title":"Feature Selective Anchor-Free Module for Single-Shot Object Detection","code":"https://github.com/open-mmlab/mmdetection","n_code_links":4,"official":null,"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":6,"n_samples":8,"n_pointer_only_licence":0,"sample_list":"/paper/feature-selective-anchor-free-module-for#ran","syntology_url":"https://syntology.ai/paper/1903.00621","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1903.00621"}}}},{"rank_in_archive_order":144,"model":"aLRP Loss (ResNext-101, DCN, 500 scale)","metrics":{"AP50":"65.0","AP75":"47.5","APL":"58.3","APM":"48.1","APS":"24.6","box mAP":"44.6"},"uses_additional_data":false,"paper_date":"2020-09-28","paper":"/paper/a-ranking-based-balanced-loss-function","paper_url":"https://arxiv.org/abs/2009.13592v4","paper_title":"A Ranking-based, Balanced Loss Function Unifying Classification and Localisation in Object Detection","code":"https://github.com/kemaloksuz/aLRPLoss","n_code_links":3,"official":{"repos":["kemaloksuz/aLRPLoss"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":1,"sample_list":"/paper/a-ranking-based-balanced-loss-function#ran","syntology_url":"https://syntology.ai/paper/2009.13592","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2009.13592"}}}},{"rank_in_archive_order":145,"model":"CenterMask + X-101-32x8d (single-scale)","metrics":{"AP50":"63.4","AP75":"48.4","APM":"47.2","box mAP":"44.6"},"uses_additional_data":false,"paper_date":"2019-11-15","paper":"/paper/centermask-real-time-anchor-free-instance-1","paper_url":"https://arxiv.org/abs/1911.06667v6","paper_title":"CenterMask : Real-Time Anchor-Free Instance Segmentation","code":"https://github.com/youngwanLEE/centermask2","n_code_links":8,"official":{"repos":["youngwanLEE/CenterMask"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2,"sample_list":"/paper/centermask-real-time-anchor-free-instance-1#ran","syntology_url":"https://syntology.ai/paper/1911.06667","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.06667"}}}},{"rank_in_archive_order":146,"model":"RetinaNet (SpineNet-49, 640x640)","metrics":{"AP50":"63.8","AP75":"47.6","APL":"61.1","APM":"47.7","APS":"25.9","box mAP":"44.3"},"uses_additional_data":false,"paper_date":"2019-12-10","paper":"/paper/spinenet-learning-scale-permuted-backbone-for","paper_url":"https://arxiv.org/abs/1912.05027v3","paper_title":"SpineNet: Learning Scale-Permuted Backbone for Recognition and Localization","code":"https://github.com/tensorflow/models/tree/master/official/vision/beta/modeling/backbones","n_code_links":13,"official":null,"syntology":null},{"rank_in_archive_order":147,"model":"YOLOF-DC5","metrics":{"AP50":"62.9","AP75":"47.5","APL":"60.4","APM":"48.5","APS":"24.0","box mAP":"44.3"},"uses_additional_data":false,"paper_date":"2021-03-17","paper":"/paper/you-only-look-one-level-feature","paper_url":"https://arxiv.org/abs/2103.09460v1","paper_title":"You Only Look One-level Feature","code":"https://github.com/open-mmlab/mmdetection","n_code_links":6,"official":null,"syntology":null},{"rank_in_archive_order":148,"model":"GFLV2 (ResNet-50)","metrics":{"AP50":"62.3","AP75":"48.5","APL":"54.1","APM":"47.7","APS":"26.8","box mAP":"44.3"},"uses_additional_data":false,"paper_date":"2020-11-25","paper":"/paper/generalized-focal-loss-v2-learning-reliable","paper_url":"https://arxiv.org/abs/2011.12885v1","paper_title":"Generalized Focal Loss V2: Learning Reliable Localization Quality Estimation for Dense Object Detection","code":"https://github.com/PaddlePaddle/PaddleDetection","n_code_links":5,"official":null,"syntology":null},{"rank_in_archive_order":149,"model":"InterNet (ResNet-101-FPN, multi-scale)","metrics":{"AP50":"67.5","AP75":"51.1","APL":"57.7","APM":"50.3","APS":"27.2","box mAP":"44.2"},"uses_additional_data":false,"paper_date":"2019-03-28","paper":"/paper/feature-intertwiner-for-object-detection-1","paper_url":"http://arxiv.org/abs/1903.11851v1","paper_title":"Feature Intertwiner for Object Detection","code":"https://github.com/hli2020/feature_intertwiner","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":150,"model":"M2Det (VGG-16, multi-scale)","metrics":{"AP50":"64.6","AP75":"49.3","APL":"55.1","APM":"47.9","APS":"29.2","Hardware Burden":"34G","box mAP":"44.2"},"uses_additional_data":false,"paper_date":"2018-11-12","paper":"/paper/m2det-a-single-shot-object-detector-based-on","paper_url":"http://arxiv.org/abs/1811.04533v3","paper_title":"M2Det: A Single-Shot Object Detector based on Multi-Level Feature Pyramid Network","code":"https://github.com/LeeDongYeun/keras-m2det","n_code_links":11,"official":null,"syntology":{"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0,"sample_list":"/paper/m2det-a-single-shot-object-detector-based-on#ran","syntology_url":"https://syntology.ai/paper/1811.04533","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.04533"}}}},{"rank_in_archive_order":151,"model":"Faster R-CNN (LIP-ResNet-101-MD w FPN)","metrics":{"AP50":"65.7","AP75":"48.1","APL":"56.3","APM":"46.7","APS":"25.4","box mAP":"43.9"},"uses_additional_data":false,"paper_date":"2019-08-12","paper":"/paper/lip-local-importance-based-pooling","paper_url":"https://arxiv.org/abs/1908.04156v3","paper_title":"LIP: Local Importance-based Pooling","code":"https://github.com/sebgao/LIP","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":152,"model":"M2Det (ResNet-101, multi-scale)","metrics":{"AP50":"64.4","AP75":"48","APL":"54.3","APM":"49.6","APS":"29.6","Hardware Burden":"27G","box mAP":"43.9"},"uses_additional_data":false,"paper_date":"2018-11-12","paper":"/paper/m2det-a-single-shot-object-detector-based-on","paper_url":"http://arxiv.org/abs/1811.04533v3","paper_title":"M2Det: A Single-Shot Object Detector based on Multi-Level Feature Pyramid Network","code":"https://github.com/LeeDongYeun/keras-m2det","n_code_links":11,"official":null,"syntology":{"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0,"sample_list":"/paper/m2det-a-single-shot-object-detector-based-on#ran","syntology_url":"https://syntology.ai/paper/1811.04533","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.04533"}}}},{"rank_in_archive_order":153,"model":"YOLOv3 @800 + ASFF* (Darknet-53)","metrics":{"AP50":" 64.1","AP75":" 49.2","APL":"53.4","APM":" 46.6","APS":"27.0","box mAP":"43.9"},"uses_additional_data":true,"paper_date":"2019-11-21","paper":"/paper/learning-spatial-fusion-for-single-shot","paper_url":"https://arxiv.org/abs/1911.09516v2","paper_title":"Learning Spatial Fusion for Single-Shot Object Detection","code":"https://github.com/ruinmessi/ASFF","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":154,"model":"FoveaBox (ResNeXt-101)","metrics":{"AP50":"63.5","AP75":"47.7","APL":"55.6","APM":"46.9","APS":"26.8","box mAP":"43.9"},"uses_additional_data":false,"paper_date":"2019-04-08","paper":"/paper/foveabox-beyond-anchor-based-object-detector","paper_url":"https://arxiv.org/abs/1904.03797v2","paper_title":"FoveaBox: Beyond Anchor-based Object Detector","code":"https://github.com/open-mmlab/mmdetection","n_code_links":7,"official":null,"syntology":null},{"rank_in_archive_order":155,"model":"ExtremeNet (Hourglass-104, multi-scale)","metrics":{"AP50":"60.5","AP75":"47.0","APL":"57.6","APM":"46.9","APS":"24.1","Hardware Burden":"180G","box mAP":"43.7"},"uses_additional_data":false,"paper_date":"2019-01-23","paper":"/paper/bottom-up-object-detection-by-grouping","paper_url":"http://arxiv.org/abs/1901.08043v3","paper_title":"Bottom-up Object Detection by Grouping Extreme and Center Points","code":"https://github.com/xingyizhou/ExtremeNet","n_code_links":2,"official":{"repos":["xingyizhou/ExtremeNet"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]},"syntology":{"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":4,"n_samples":5,"n_pointer_only_licence":0,"sample_list":"/paper/bottom-up-object-detection-by-grouping#ran","syntology_url":"https://syntology.ai/paper/1901.08043","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.08043"}}}},{"rank_in_archive_order":156,"model":"YOLOv4-608","metrics":{"AP50":"65.7","AP75":"47.3","APL":"53.3","APM":"46.7","APS":"26.7","box mAP":"43.5"},"uses_additional_data":true,"paper_date":"2020-04-23","paper":"/paper/yolov4-optimal-speed-and-accuracy-of-object","paper_url":"https://arxiv.org/abs/2004.10934v1","paper_title":"YOLOv4: Optimal Speed and Accuracy of Object Detection","code":"https://github.com/tensorflow/models/tree/master/official/vision/beta/projects/yolo","n_code_links":223,"official":{"repos":["AlexeyAB/darknet"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":142,"n_constructed":0,"n_ran_checked":128,"n_instrument":14,"n_unverified":42,"n_samples":184,"n_pointer_only_licence":21,"sample_list":"/paper/yolov4-optimal-speed-and-accuracy-of-object#ran","syntology_url":"https://syntology.ai/paper/2004.10934","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.10934"}}}},{"rank_in_archive_order":157,"model":"SNIPER (ResNet-50)","metrics":{"AP50":"65.0","AP75":"48.6","APL":"56.0","APM":"46.3","APS":"26.1","Hardware Burden":"29G","box mAP":"43.5"},"uses_additional_data":false,"paper_date":"2018-05-23","paper":"/paper/sniper-efficient-multi-scale-training","paper_url":"http://arxiv.org/abs/1805.09300v3","paper_title":"SNIPER: Efficient Multi-Scale Training","code":"https://github.com/PaddlePaddle/PaddleDetection","n_code_links":4,"official":null,"syntology":null},{"rank_in_archive_order":158,"model":"CenterNet (HRNetV2-W48)","metrics":{"AP75":"46.5","APL":"57.8","APS":"22.2","Hardware Burden":"16G","Operations per network pass":"21.7G","box mAP":"43.5"},"uses_additional_data":false,"paper_date":"2019-08-20","paper":"/paper/190807919","paper_url":"https://arxiv.org/abs/1908.07919v2","paper_title":"Deep High-Resolution Representation Learning for Visual Recognition","code":"https://github.com/open-mmlab/mmdetection","n_code_links":42,"official":null,"syntology":{"n_ran":21,"n_constructed":0,"n_ran_checked":16,"n_instrument":5,"n_unverified":13,"n_samples":34,"n_pointer_only_licence":21,"sample_list":"/paper/190807919#ran","syntology_url":"https://syntology.ai/paper/1908.07919","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.07919"}}}},{"rank_in_archive_order":159,"model":"D-RFCN + SNIP (ResNet-101, multi-scale)","metrics":{"AP50":"65.5","AP75":"48.4","APL":"54.9","APM":"46.5","APS":"27.2","box mAP":"43.4"},"uses_additional_data":false,"paper_date":"2017-11-22","paper":"/paper/an-analysis-of-scale-invariance-in-object-1","paper_url":"http://arxiv.org/abs/1711.08189v2","paper_title":"An Analysis of Scale Invariance in Object Detection - SNIP","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":160,"model":"Grid R-CNN (ResNeXt-101-FPN)","metrics":{"AP50":"63.0","AP75":"46.6","APL":"55.2","APM":"46.5","APS":"25.1","box mAP":"43.2"},"uses_additional_data":false,"paper_date":"2018-11-29","paper":"/paper/grid-r-cnn","paper_url":"http://arxiv.org/abs/1811.12030v1","paper_title":"Grid R-CNN","code":"https://github.com/open-mmlab/mmdetection","n_code_links":2,"official":null,"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":0,"sample_list":"/paper/grid-r-cnn#ran","syntology_url":"https://syntology.ai/paper/1811.12030","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.12030"}}}},{"rank_in_archive_order":161,"model":"FCOS (ResNeXt-101-64x4d-FPN)","metrics":{"AP50":"62.8","AP75":"46.6 ","APL":"53.3","APM":"46.2","APS":"26.5","box mAP":"43.2"},"uses_additional_data":false,"paper_date":"2019-04-02","paper":"/paper/fcos-fully-convolutional-one-stage-object","paper_url":"https://arxiv.org/abs/1904.01355v5","paper_title":"FCOS: Fully Convolutional One-Stage Object Detection","code":"https://github.com/open-mmlab/mmdetection","n_code_links":87,"official":{"repos":["tianzhi0549/FCOS"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]},"syntology":{"n_ran":37,"n_constructed":0,"n_ran_checked":30,"n_instrument":7,"n_unverified":3,"n_samples":40,"n_pointer_only_licence":19,"sample_list":"/paper/fcos-fully-convolutional-one-stage-object#ran","syntology_url":"https://syntology.ai/paper/1904.01355","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.01355"}}}},{"rank_in_archive_order":162,"model":"CornerNet-Saccade (Hourglass-104, multi-scale)","metrics":{"APL":"57.3","APM":"44.6","APS":"24.4","box mAP":"43.2"},"uses_additional_data":false,"paper_date":"2019-04-18","paper":"/paper/190408900","paper_url":"https://arxiv.org/abs/1904.08900v2","paper_title":"CornerNet-Lite: Efficient Keypoint Based Object Detection","code":"https://github.com/PaddlePaddle/PaddleDetection","n_code_links":6,"official":{"repos":["princeton-vl/CornerNet-Lite"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":21,"n_constructed":0,"n_ran_checked":21,"n_instrument":0,"n_unverified":6,"n_samples":27,"n_pointer_only_licence":0,"sample_list":"/paper/190408900#ran","syntology_url":"https://syntology.ai/paper/1904.08900","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.08900"}}}},{"rank_in_archive_order":163,"model":"PP-YOLOE-s(CSPRepResNet-s, 640x640, single-scale )","metrics":{"AP50":"60.5","AP75":"46.6","APL":"56.9","APM":"46.4","APS":"23.2","box mAP":"43.1"},"uses_additional_data":false,"paper_date":"2022-03-30","paper":"/paper/pp-yoloe-an-evolved-version-of-yolo","paper_url":"https://arxiv.org/abs/2203.16250v3","paper_title":"PP-YOLOE: An evolved version of YOLO","code":"https://github.com/PaddlePaddle/PaddleDetection","n_code_links":8,"official":{"repos":["PaddlePaddle/PaddleDetection"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":22,"n_constructed":0,"n_ran_checked":19,"n_instrument":3,"n_unverified":5,"n_samples":27,"n_pointer_only_licence":1,"sample_list":"/paper/pp-yoloe-an-evolved-version-of-yolo#ran","syntology_url":"https://syntology.ai/paper/2203.16250","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.16250"}}}},{"rank_in_archive_order":164,"model":"Libra R-CNN (ResNeXt-101-FPN)","metrics":{"AP50":"64","AP75":"47","APL":"54.6","APM":"45.6","APS":"25.3","box mAP":"43.0"},"uses_additional_data":false,"paper_date":"2019-04-04","paper":"/paper/libra-r-cnn-towards-balanced-learning-for","paper_url":"http://arxiv.org/abs/1904.02701v1","paper_title":"Libra R-CNN: Towards Balanced Learning for Object Detection","code":"https://github.com/open-mmlab/mmdetection","n_code_links":6,"official":null,"syntology":null},{"rank_in_archive_order":165,"model":"DyHead (ResNet-50)","metrics":{"AP50":"60.7","AP75":"46.8","box mAP":"43"},"uses_additional_data":false,"paper_date":"2021-06-15","paper":"/paper/dynamic-head-unifying-object-detection-heads","paper_url":"https://arxiv.org/abs/2106.08322v1","paper_title":"Dynamic Head: Unifying Object Detection Heads with Attentions","code":"https://github.com/open-mmlab/mmdetection","n_code_links":3,"official":{"repos":["microsoft/DynamicHead"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":8,"n_constructed":5,"n_ran_checked":6,"n_instrument":2,"n_unverified":1,"n_samples":9,"n_pointer_only_licence":0,"sample_list":"/paper/dynamic-head-unifying-object-detection-heads#ran","syntology_url":"https://syntology.ai/paper/2106.08322","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.08322"}}}},{"rank_in_archive_order":166,"model":"RPDet (ResNet-101-DCN)","metrics":{"AP50":"65.0","AP75":"46.3","APL":"54.7","APM":"46.2","APS":"24.9","box mAP":"42.8"},"uses_additional_data":false,"paper_date":"2019-04-25","paper":"/paper/reppoints-point-set-representation-for-object","paper_url":"https://arxiv.org/abs/1904.11490v2","paper_title":"RepPoints: Point Set Representation for Object Detection","code":"https://github.com/open-mmlab/mmdetection","n_code_links":6,"official":{"repos":["microsoft/RepPoints"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":3,"sample_list":"/paper/reppoints-point-set-representation-for-object#ran","syntology_url":"https://syntology.ai/paper/1904.11490","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.11490"}}}},{"rank_in_archive_order":167,"model":"SpineNet-49 (640, RetinaNet, single-scale)","metrics":{"AP50":"62.3","AP75":"46.1","APL":"57.3","APM":"45.2","APS":"23.7","box mAP":"42.8"},"uses_additional_data":false,"paper_date":"2019-12-10","paper":"/paper/spinenet-learning-scale-permuted-backbone-for","paper_url":"https://arxiv.org/abs/1912.05027v3","paper_title":"SpineNet: Learning Scale-Permuted Backbone for Recognition and Localization","code":"https://github.com/tensorflow/models/tree/master/official/vision/beta/modeling/backbones","n_code_links":13,"official":null,"syntology":null},{"rank_in_archive_order":168,"model":"Cascade R-CNN (ResNet-101-FPN+, cascade)","metrics":{"AP50":"62.1","AP75":"46.3","APL":"55.2","APM":"45.5","APS":"23.7","box mAP":"42.8"},"uses_additional_data":false,"paper_date":"2017-12-03","paper":"/paper/cascade-r-cnn-delving-into-high-quality","paper_url":"http://arxiv.org/abs/1712.00726v1","paper_title":"Cascade R-CNN: Delving into High Quality Object Detection","code":"https://github.com/open-mmlab/mmdetection","n_code_links":8,"official":{"repos":["zhaoweicai/cascade-rcnn"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2,"sample_list":"/paper/cascade-r-cnn-delving-into-high-quality#ran","syntology_url":"https://syntology.ai/paper/1712.00726","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1712.00726"}}}},{"rank_in_archive_order":169,"model":"Cascade R-CNN","metrics":{"AP50":"62.1","AP75":"46.3","APL":"55.2","APM":"45.5","APS":"23.7","Hardware Burden":"15G","box mAP":"42.8"},"uses_additional_data":false,"paper_date":"2019-06-24","paper":"/paper/cascade-r-cnn-high-quality-object-detection","paper_url":"https://arxiv.org/abs/1906.09756v1","paper_title":"Cascade R-CNN: High Quality Object Detection and Instance Segmentation","code":"https://github.com/open-mmlab/mmdetection","n_code_links":4,"official":null,"syntology":null},{"rank_in_archive_order":170,"model":"TridentNet (ResNet-101)","metrics":{"AP50":"63.6","AP75":"46.5","APL":"56.6","APM":"46.6","APS":"23.9","box mAP":"42.7"},"uses_additional_data":false,"paper_date":"2019-01-07","paper":"/paper/scale-aware-trident-networks-for-object","paper_url":"https://arxiv.org/abs/1901.01892v2","paper_title":"Scale-Aware Trident Networks for Object Detection","code":"https://github.com/facebookresearch/detectron2/tree/master/projects/TridentNet/","n_code_links":4,"official":null,"syntology":null},{"rank_in_archive_order":171,"model":"FCOS (ResNeXt-32x8d-101-FPN)","metrics":{"AP50":"62.2","AP75":"46.1","APL":"52.6","APM":"45.6","APS":"26.0","box mAP":"42.7"},"uses_additional_data":false,"paper_date":"2019-04-02","paper":"/paper/fcos-fully-convolutional-one-stage-object","paper_url":"https://arxiv.org/abs/1904.01355v5","paper_title":"FCOS: Fully Convolutional One-Stage Object Detection","code":"https://github.com/open-mmlab/mmdetection","n_code_links":87,"official":{"repos":["tianzhi0549/FCOS"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]},"syntology":{"n_ran":37,"n_constructed":0,"n_ran_checked":30,"n_instrument":7,"n_unverified":3,"n_samples":40,"n_pointer_only_licence":19,"sample_list":"/paper/fcos-fully-convolutional-one-stage-object#ran","syntology_url":"https://syntology.ai/paper/1904.01355","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.01355"}}}},{"rank_in_archive_order":172,"model":"RetinaMask (ResNeXt-101-FPN-GN)","metrics":{"AP50":"62.5","AP75":"46.0","APL":"53.8","APM":"45.6","APS":"24.8","Hardware Burden":"12G","box mAP":"42.6"},"uses_additional_data":false,"paper_date":"2019-01-10","paper":"/paper/retinamask-learning-to-predict-masks-improves","paper_url":"http://arxiv.org/abs/1901.03353v1","paper_title":"RetinaMask: Learning to predict masks improves state-of-the-art single-shot detection for free","code":"https://github.com/chengyangfu/retinamask","n_code_links":53,"official":null,"syntology":null},{"rank_in_archive_order":173,"model":"TAL + TAP","metrics":{"AP50":"60.3","AP75":"46.4","box mAP":"42.5"},"uses_additional_data":false,"paper_date":"2021-08-17","paper":"/paper/tood-task-aligned-one-stage-object-detection","paper_url":"https://arxiv.org/abs/2108.07755v3","paper_title":"TOOD: Task-aligned One-stage Object Detection","code":"https://github.com/open-mmlab/mmdetection","n_code_links":6,"official":{"repos":["fcjian/TOOD"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":2,"n_samples":4,"n_pointer_only_licence":3,"sample_list":"/paper/tood-task-aligned-one-stage-object-detection#ran","syntology_url":"https://syntology.ai/paper/2108.07755","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.07755"}}}},{"rank_in_archive_order":174,"model":"Faster R-CNN (HRNetV2p-W48)","metrics":{"AP50":"63.6","AP75":"46.4","APL":"53.0","APM":"44.6","APS":"24.9","Hardware Burden":"16G","Operations per network pass":"20.8G","box mAP":"42.4"},"uses_additional_data":false,"paper_date":"2019-08-20","paper":"/paper/190807919","paper_url":"https://arxiv.org/abs/1908.07919v2","paper_title":"Deep High-Resolution Representation Learning for Visual Recognition","code":"https://github.com/open-mmlab/mmdetection","n_code_links":42,"official":null,"syntology":{"n_ran":21,"n_constructed":0,"n_ran_checked":16,"n_instrument":5,"n_unverified":13,"n_samples":34,"n_pointer_only_licence":21,"sample_list":"/paper/190807919#ran","syntology_url":"https://syntology.ai/paper/1908.07919","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.07919"}}}},{"rank_in_archive_order":175,"model":"HSD (Rest101, 768x768, single-scale test)","metrics":{"AP50":"61.2","AP75":"46.9","APL":"55.9","APM":"47.3","APS":"22.8","box mAP":"42.3"},"uses_additional_data":false,"paper_date":"2019-10-01","paper":"/paper/hierarchical-shot-detector","paper_url":"http://openaccess.thecvf.com/content_ICCV_2019/html/Cao_Hierarchical_Shot_Detector_ICCV_2019_paper.html","paper_title":"Hierarchical Shot Detector","code":"https://github.com/JialeCao001/HSD","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":176,"model":"CornerNet511 (Hourglass-104, multi-scale)","metrics":{"AP50":"57.8","AP75":"45.3","APL":"56.7","APM":"44.8","APS":"20.8","box mAP":"42.1"},"uses_additional_data":false,"paper_date":"2018-08-03","paper":"/paper/cornernet-detecting-objects-as-paired","paper_url":"http://arxiv.org/abs/1808.01244v2","paper_title":"CornerNet: Detecting Objects as Paired Keypoints","code":"https://github.com/open-mmlab/mmdetection","n_code_links":5,"official":{"repos":["princeton-vl/CornerNet"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":8,"ran_from_kinds":["official"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":8,"n_samples":11,"n_pointer_only_licence":2,"sample_list":"/paper/cornernet-detecting-objects-as-paired#ran","syntology_url":"https://syntology.ai/paper/1808.01244","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1808.01244"}}}},{"rank_in_archive_order":177,"model":"FoveaBox (ResNeXt-101)","metrics":{"box mAP":"42.1"},"uses_additional_data":false,"paper_date":"2019-04-08","paper":"/paper/foveabox-beyond-anchor-based-object-detector","paper_url":"https://arxiv.org/abs/1904.03797v2","paper_title":"FoveaBox: Beyond Anchor-based Object Detector","code":"https://github.com/open-mmlab/mmdetection","n_code_links":7,"official":null,"syntology":null},{"rank_in_archive_order":178,"model":"FCOS (HRNet-W32-5l)","metrics":{"AP50":"60.4","AP75":"45.3","APL":"51.0","APM":"45.0","APS":"25.4","box mAP":"42.0"},"uses_additional_data":false,"paper_date":"2019-04-02","paper":"/paper/fcos-fully-convolutional-one-stage-object","paper_url":"https://arxiv.org/abs/1904.01355v5","paper_title":"FCOS: Fully Convolutional One-Stage Object Detection","code":"https://github.com/open-mmlab/mmdetection","n_code_links":87,"official":{"repos":["tianzhi0549/FCOS"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]},"syntology":{"n_ran":37,"n_constructed":0,"n_ran_checked":30,"n_instrument":7,"n_unverified":3,"n_samples":40,"n_pointer_only_licence":19,"sample_list":"/paper/fcos-fully-convolutional-one-stage-object#ran","syntology_url":"https://syntology.ai/paper/1904.01355","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.01355"}}}},{"rank_in_archive_order":179,"model":"FoveaBox (ResNeXt-101)","metrics":{"box mAP":"41.9"},"uses_additional_data":false,"paper_date":"2019-04-08","paper":"/paper/foveabox-beyond-anchor-based-object-detector","paper_url":"https://arxiv.org/abs/1904.03797v2","paper_title":"FoveaBox: Beyond Anchor-based Object Detector","code":"https://github.com/open-mmlab/mmdetection","n_code_links":7,"official":null,"syntology":null},{"rank_in_archive_order":180,"model":"RefineDet512+ (ResNet-101)","metrics":{"AP50":"62.9","AP75":"45.7","APL":"54.1","APM":"45.1","APS":"25.6","box mAP":"41.8"},"uses_additional_data":false,"paper_date":"2017-11-18","paper":"/paper/single-shot-refinement-neural-network-for","paper_url":"http://arxiv.org/abs/1711.06897v3","paper_title":"Single-Shot Refinement Neural Network for Object Detection","code":"https://github.com/sfzhang15/RefineDet","n_code_links":16,"official":null,"syntology":null},{"rank_in_archive_order":181,"model":"GHM-C + GHM-R (RetinaNet-FPN-ResNeXt-101)","metrics":{"AP50":"62.8","AP75":"44.2","APL":"55.3","APM":"45.1","APS":"22.3","box mAP":"41.6"},"uses_additional_data":false,"paper_date":"2018-11-13","paper":"/paper/gradient-harmonized-single-stage-detector","paper_url":"http://arxiv.org/abs/1811.05181v1","paper_title":"Gradient Harmonized Single-stage Detector","code":"https://github.com/open-mmlab/mmdetection","n_code_links":9,"official":{"repos":["libuyu/GHM_Detection"],"state":"official: not harvested","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]},"syntology":{"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0,"sample_list":"/paper/gradient-harmonized-single-stage-detector#ran","syntology_url":"https://syntology.ai/paper/1811.05181","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.05181"}}}},{"rank_in_archive_order":182,"model":"CenterNet-DLA (DLA-34, multi-scale)","metrics":{"APL":"56.0","APM":"43.9","APS":"21.5","Hardware Burden":"26G","box mAP":"41.6"},"uses_additional_data":false,"paper_date":"2019-04-16","paper":"/paper/objects-as-points","paper_url":"http://arxiv.org/abs/1904.07850v2","paper_title":"Objects as Points","code":"https://github.com/tensorflow/models/tree/master/research/object_detection","n_code_links":76,"official":{"repos":["xingyizhou/CenterNet"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":5,"ran_from_kinds":["listed"]},"syntology":{"n_ran":77,"n_constructed":0,"n_ran_checked":66,"n_instrument":11,"n_unverified":53,"n_samples":130,"n_pointer_only_licence":2,"sample_list":"/paper/objects-as-points#ran","syntology_url":"https://syntology.ai/paper/1904.07850","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.07850"}}}},{"rank_in_archive_order":183,"model":"RetinaNet (SpineNet-49S, 640x640)","metrics":{"AP50":"60.5","AP75":"44.6","APL":"58","APM":"45","APS":"23.3","box mAP":"41.5"},"uses_additional_data":false,"paper_date":"2019-12-10","paper":"/paper/spinenet-learning-scale-permuted-backbone-for","paper_url":"https://arxiv.org/abs/1912.05027v3","paper_title":"SpineNet: Learning Scale-Permuted Backbone for Recognition and Localization","code":"https://github.com/tensorflow/models/tree/master/official/vision/beta/modeling/backbones","n_code_links":13,"official":null,"syntology":null},{"rank_in_archive_order":184,"model":"RPDet (ResNet-101)","metrics":{"AP50":"62.9","AP75":"44.3","APL":"51.7","APM":"44.1","APS":"23.6","box mAP":"41"},"uses_additional_data":false,"paper_date":"2019-04-25","paper":"/paper/reppoints-point-set-representation-for-object","paper_url":"https://arxiv.org/abs/1904.11490v2","paper_title":"RepPoints: Point Set Representation for Object Detection","code":"https://github.com/open-mmlab/mmdetection","n_code_links":6,"official":{"repos":["microsoft/RepPoints"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":3,"sample_list":"/paper/reppoints-point-set-representation-for-object#ran","syntology_url":"https://syntology.ai/paper/1904.11490","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.11490"}}}},{"rank_in_archive_order":185,"model":"M2Det (VGG-16, single-scale)","metrics":{"AP50":"59.7","AP75":"45","APL":"53.8","APM":"46.5","APS":"22.1","Hardware Burden":"34G","box mAP":"41.0"},"uses_additional_data":false,"paper_date":"2018-11-12","paper":"/paper/m2det-a-single-shot-object-detector-based-on","paper_url":"http://arxiv.org/abs/1811.04533v3","paper_title":"M2Det: A Single-Shot Object Detector based on Multi-Level Feature Pyramid Network","code":"https://github.com/LeeDongYeun/keras-m2det","n_code_links":11,"official":null,"syntology":{"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0,"sample_list":"/paper/m2det-a-single-shot-object-detector-based-on#ran","syntology_url":"https://syntology.ai/paper/1811.04533","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.04533"}}}},{"rank_in_archive_order":186,"model":"LeYOLO (Large@768)","metrics":{"GFLOPs":"8.4","Params (M)":"2.4","box mAP":"41.0"},"uses_additional_data":false,"paper_date":"2024-06-20","paper":"/paper/leyolo-new-scalable-and-efficient-cnn","paper_url":"https://arxiv.org/abs/2406.14239v1","paper_title":"LeYOLO, New Scalable and Efficient CNN Architecture for Object Detection","code":"https://github.com/LilianHollard/LeYOLO","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":187,"model":"FSAF (ResNet-101, single-scale)","metrics":{"AP50":"61.5","AP75":"44","APL":"51.3","APM":"44.2","APS":"24","Hardware Burden":"38G","box mAP":"40.9"},"uses_additional_data":false,"paper_date":"2019-03-02","paper":"/paper/feature-selective-anchor-free-module-for","paper_url":"http://arxiv.org/abs/1903.00621v1","paper_title":"Feature Selective Anchor-Free Module for Single-Shot Object Detection","code":"https://github.com/open-mmlab/mmdetection","n_code_links":4,"official":null,"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":6,"n_samples":8,"n_pointer_only_licence":0,"sample_list":"/paper/feature-selective-anchor-free-module-for#ran","syntology_url":"https://syntology.ai/paper/1903.00621","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1903.00621"}}}},{"rank_in_archive_order":188,"model":"RetinaNet (ResNeXt-101-FPN)","metrics":{"AP50":"61.1","AP75":"44.1","APL":"51.2","APM":"44.2","APS":"24.1","Hardware Burden":"4G","box mAP":"40.8"},"uses_additional_data":false,"paper_date":"2017-08-07","paper":"/paper/focal-loss-for-dense-object-detection","paper_url":"http://arxiv.org/abs/1708.02002v2","paper_title":"Focal Loss for Dense Object Detection","code":"https://github.com/tensorflow/models","n_code_links":234,"official":{"repos":["facebookresearch/detectron"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":11,"n_constructed":0,"n_ran_checked":2,"n_instrument":9,"n_unverified":0,"n_samples":11,"n_pointer_only_licence":6,"sample_list":"/paper/focal-loss-for-dense-object-detection#ran","syntology_url":"https://syntology.ai/paper/1708.02002","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1708.02002"}}}},{"rank_in_archive_order":189,"model":"Cascade R-CNN (ResNet-50-FPN+, cascade)","metrics":{"AP50":"59.9","AP75":"44","APL":"52.1","APM":"42.7","APS":"22.6","Hardware Burden":"12G","box mAP":"40.6"},"uses_additional_data":false,"paper_date":"2017-12-03","paper":"/paper/cascade-r-cnn-delving-into-high-quality","paper_url":"http://arxiv.org/abs/1712.00726v1","paper_title":"Cascade R-CNN: Delving into High Quality Object Detection","code":"https://github.com/open-mmlab/mmdetection","n_code_links":8,"official":{"repos":["zhaoweicai/cascade-rcnn"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2,"sample_list":"/paper/cascade-r-cnn-delving-into-high-quality#ran","syntology_url":"https://syntology.ai/paper/1712.00726","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1712.00726"}}}},{"rank_in_archive_order":190,"model":"Faster R-CNN (Cascade RPN)","metrics":{"AP50":"58.9","AP75":"44.5","APL":"52.6","APM":"42.8","APS":"22.0","Hardware Burden":"5G","box mAP":"40.6"},"uses_additional_data":true,"paper_date":"2019-09-15","paper":"/paper/cascade-rpn-delving-into-high-quality-region","paper_url":"https://arxiv.org/abs/1909.06720v2","paper_title":"Cascade RPN: Delving into High-Quality Region Proposal Network with Adaptive Convolution","code":"https://github.com/open-mmlab/mmdetection","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":191,"model":"ResNet-50-DW-DPN (Deformable Kernels)","metrics":{"APL":"53.3","APM":"43.9","APS":"24.6","box mAP":"40.6"},"uses_additional_data":false,"paper_date":"2019-10-07","paper":"/paper/deformable-kernels-adapting-effective","paper_url":"https://arxiv.org/abs/1910.02940v2","paper_title":"Deformable Kernels: Adapting Effective Receptive Fields for Object Deformation","code":"https://github.com/hangg7/deformable-kernels","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":192,"model":"IoU-Net","metrics":{"box mAP":"40.6"},"uses_additional_data":false,"paper_date":"2018-07-30","paper":"/paper/acquisition-of-localization-confidence-for","paper_url":"http://arxiv.org/abs/1807.11590v1","paper_title":"Acquisition of Localization Confidence for Accurate Object Detection","code":"https://github.com/vacancy/PreciseRoIPooling","n_code_links":4,"official":{"repos":["vacancy/PreciseRoIPooling"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":17,"n_constructed":0,"n_ran_checked":13,"n_instrument":4,"n_unverified":1,"n_samples":18,"n_pointer_only_licence":2,"sample_list":"/paper/acquisition-of-localization-confidence-for#ran","syntology_url":"https://syntology.ai/paper/1807.11590","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1807.11590"}}}},{"rank_in_archive_order":193,"model":"FCOS (HRNetV2p-W48)","metrics":{"AP50":"59.3","APL":"51.0","APM":"42.6","APS":"23.4","Hardware Burden":"16G","Operations per network pass":"27.3G","box mAP":"40.5"},"uses_additional_data":true,"paper_date":"2019-08-20","paper":"/paper/190807919","paper_url":"https://arxiv.org/abs/1908.07919v2","paper_title":"Deep High-Resolution Representation Learning for Visual Recognition","code":"https://github.com/open-mmlab/mmdetection","n_code_links":42,"official":null,"syntology":{"n_ran":21,"n_constructed":0,"n_ran_checked":16,"n_instrument":5,"n_unverified":13,"n_samples":34,"n_pointer_only_licence":21,"sample_list":"/paper/190807919#ran","syntology_url":"https://syntology.ai/paper/1908.07919","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.07919"}}}},{"rank_in_archive_order":194,"model":"ResNet-50-FPN Mask R-CNN + KL Loss + var voting + soft-NMS","metrics":{"box mAP":"40.4"},"uses_additional_data":false,"paper_date":"2018-09-23","paper":"/paper/softer-nms-rethinking-bounding-box-regression","paper_url":"http://arxiv.org/abs/1809.08545v3","paper_title":"Bounding Box Regression with Uncertainty for Accurate Object Detection","code":"https://github.com/yihui-he/KL-Loss","n_code_links":4,"official":{"repos":["yihui-he/softer-NMS","yihui-he/KL-Loss"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":2,"n_samples":4,"n_pointer_only_licence":0,"sample_list":"/paper/softer-nms-rethinking-bounding-box-regression#ran","syntology_url":"https://syntology.ai/paper/1809.08545","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1809.08545"}}}},{"rank_in_archive_order":195,"model":"RDSNet (ResNet-101, RetinaNet, mask, MBRM)","metrics":{"AP50":"60.1","AP75":"43","APL":"51.5","APM":"43.5","APS":"22.1","box mAP":"40.3"},"uses_additional_data":false,"paper_date":"2019-12-11","paper":"/paper/rdsnet-a-new-deep-architecture-for-reciprocal","paper_url":"https://arxiv.org/abs/1912.05070v1","paper_title":"RDSNet: A New Deep Architecture for Reciprocal Object Detection and Instance Segmentation","code":"https://github.com/wangsr126/RDSNet","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":196,"model":"ExtremeNet (Hourglass-104, single-scale)","metrics":{"AP50":"55.5","AP75":"43.2","APL":"53.1","APM":"43.2","APS":"20.4","Hardware Burden":"180G","box mAP":"40.2"},"uses_additional_data":false,"paper_date":"2019-01-23","paper":"/paper/bottom-up-object-detection-by-grouping","paper_url":"http://arxiv.org/abs/1901.08043v3","paper_title":"Bottom-up Object Detection by Grouping Extreme and Center Points","code":"https://github.com/xingyizhou/ExtremeNet","n_code_links":2,"official":{"repos":["xingyizhou/ExtremeNet"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]},"syntology":{"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":4,"n_samples":5,"n_pointer_only_licence":0,"sample_list":"/paper/bottom-up-object-detection-by-grouping#ran","syntology_url":"https://syntology.ai/paper/1901.08043","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.08043"}}}},{"rank_in_archive_order":197,"model":"Mask R-CNN (ResNet-101-FPN, CBN)","metrics":{"AP50":"60.5","AP75":"44.1","APL":"38.5","APM":"57.3","APS":"35.8","box mAP":"40.1"},"uses_additional_data":false,"paper_date":"2020-02-13","paper":"/paper/cross-iteration-batch-normalization","paper_url":"https://arxiv.org/abs/2002.05712v3","paper_title":"Cross-Iteration Batch Normalization","code":"https://github.com/Howal/Cross-iterationBatchNorm","n_code_links":2,"official":{"repos":["Howal/Cross-iterationBatchNorm"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":2,"n_samples":6,"n_pointer_only_licence":1,"sample_list":"/paper/cross-iteration-batch-normalization#ran","syntology_url":"https://syntology.ai/paper/2002.05712","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.05712"}}}},{"rank_in_archive_order":198,"model":"Fast R-CNN (Cascade RPN)","metrics":{"AP50":"59.4","AP75":"43.8","APL":"51.6","APM":"42.4","APS":"22.1","Hardware Burden":"5G","box mAP":"40.1"},"uses_additional_data":true,"paper_date":"2019-09-15","paper":"/paper/cascade-rpn-delving-into-high-quality-region","paper_url":"https://arxiv.org/abs/1909.06720v2","paper_title":"Cascade RPN: Delving into High-Quality Region Proposal Network with Adaptive Convolution","code":"https://github.com/open-mmlab/mmdetection","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":199,"model":"Mask R-CNN (ResNeXt-101-FPN)","metrics":{"AP50":"62.3","AP75":"43.4","APL":"51.2","APM":"43.2","APS":"22.1","Hardware Burden":"9G","box mAP":"39.8"},"uses_additional_data":false,"paper_date":"2017-03-20","paper":"/paper/mask-r-cnn","paper_url":"http://arxiv.org/abs/1703.06870v3","paper_title":"Mask R-CNN","code":"https://github.com/tensorflow/models/tree/master/official/vision","n_code_links":179,"official":null,"syntology":{"n_ran":101,"n_constructed":3,"n_ran_checked":77,"n_instrument":24,"n_unverified":39,"n_samples":140,"n_pointer_only_licence":32,"sample_list":"/paper/mask-r-cnn#ran","syntology_url":"https://syntology.ai/paper/1703.06870","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1703.06870"}}}},{"rank_in_archive_order":200,"model":"GA-Faster-RCNN","metrics":{"AP50":"59.2","AP75":"43.5","APL":"50.7","APM":"42.6","APS":"21.8","box mAP":"39.8"},"uses_additional_data":false,"paper_date":"2019-01-10","paper":"/paper/region-proposal-by-guided-anchoring","paper_url":"http://arxiv.org/abs/1901.03278v2","paper_title":"Region Proposal by Guided Anchoring","code":"https://github.com/open-mmlab/mmdetection","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":201,"model":"ResNet-50 NAS-FCOS @256","metrics":{"box mAP":"39.8"},"uses_additional_data":false,"paper_date":"2019-06-11","paper":"/paper/nas-fcos-fast-neural-architecture-search-for","paper_url":"https://arxiv.org/abs/1906.04423v4","paper_title":"NAS-FCOS: Fast Neural Architecture Search for Object Detection","code":"https://github.com/open-mmlab/mmdetection","n_code_links":3,"official":null,"syntology":{"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":0,"n_samples":7,"n_pointer_only_licence":1,"sample_list":"/paper/nas-fcos-fast-neural-architecture-search-for#ran","syntology_url":"https://syntology.ai/paper/1906.04423","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.04423"}}}},{"rank_in_archive_order":202,"model":"A2MIM (ResNet-50 2x)","metrics":{"box mAP":"39.8"},"uses_additional_data":false,"paper_date":"2022-05-27","paper":"/paper/architecture-agnostic-masked-image-modeling","paper_url":"https://arxiv.org/abs/2205.13943v4","paper_title":"Architecture-Agnostic Masked Image Modeling -- From ViT back to CNN","code":"https://github.com/open-mmlab/mmpretrain","n_code_links":3,"official":null,"syntology":null},{"rank_in_archive_order":203,"model":"FPN (ResNet101 backbone)","metrics":{"box mAP":"39.5"},"uses_additional_data":false,"paper_date":"2017-08-28","paper":"/paper/chainercv-a-library-for-deep-learning-in","paper_url":"http://arxiv.org/abs/1708.08169v1","paper_title":"ChainerCV: a Library for Deep Learning in Computer Vision","code":"https://github.com/pfnet/chainercv","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":204,"model":"RetinaMask (ResNet-50-FPN)","metrics":{"AP50":"58.6","AP75":"42.3","APL":"51.0","APM":"42.0","APS":"21.9","Hardware Burden":"9G","box mAP":"39.4"},"uses_additional_data":false,"paper_date":"2019-01-10","paper":"/paper/retinamask-learning-to-predict-masks-improves","paper_url":"http://arxiv.org/abs/1901.03353v1","paper_title":"RetinaMask: Learning to predict masks improves state-of-the-art single-shot detection for free","code":"https://github.com/chengyangfu/retinamask","n_code_links":53,"official":null,"syntology":null},{"rank_in_archive_order":205,"model":"LeYOLO (Medium@640)","metrics":{"GFLOPs":"5.8","box mAP":"39.3"},"uses_additional_data":false,"paper_date":"2024-06-20","paper":"/paper/leyolo-new-scalable-and-efficient-cnn","paper_url":"https://arxiv.org/abs/2406.14239v1","paper_title":"LeYOLO, New Scalable and Efficient CNN Architecture for Object Detection","code":"https://github.com/LilianHollard/LeYOLO","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":206,"model":"AA-ResNet-10 + RetinaNet","metrics":{"Operations per network pass":"24.5G","box mAP":"39.2"},"uses_additional_data":false,"paper_date":"2019-04-22","paper":"/paper/190409925","paper_url":"https://arxiv.org/abs/1904.09925v5","paper_title":"Attention Augmented Convolutional Networks","code":"https://github.com/leaderj1001/Attention-Augmented-Conv2d","n_code_links":14,"official":null,"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":3,"n_samples":6,"n_pointer_only_licence":1,"sample_list":"/paper/190409925#ran","syntology_url":"https://syntology.ai/paper/1904.09925","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.09925"}}}},{"rank_in_archive_order":207,"model":"MAL (ResNet50, single-scale)","metrics":{"box mAP":"39.2"},"uses_additional_data":false,"paper_date":"2019-12-04","paper":"/paper/multiple-anchor-learning-for-visual-object","paper_url":"https://arxiv.org/abs/1912.02252v1","paper_title":"Multiple Anchor Learning for Visual Object Detection","code":"https://github.com/KevinKecc/MAL","n_code_links":3,"official":null,"syntology":{"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":3,"n_samples":10,"n_pointer_only_licence":1,"sample_list":"/paper/multiple-anchor-learning-for-visual-object#ran","syntology_url":"https://syntology.ai/paper/1912.02252","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.02252"}}}},{"rank_in_archive_order":208,"model":"RetinaNet (ResNet-101-FPN)","metrics":{"AP50":"59.1","AP75":"42.3","APL":"50.2","APM":"42.7","APS":"21.8","Hardware Burden":"4G","box mAP":"39.1"},"uses_additional_data":false,"paper_date":"2017-08-07","paper":"/paper/focal-loss-for-dense-object-detection","paper_url":"http://arxiv.org/abs/1708.02002v2","paper_title":"Focal Loss for Dense Object Detection","code":"https://github.com/tensorflow/models","n_code_links":234,"official":{"repos":["facebookresearch/detectron"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":11,"n_constructed":0,"n_ran_checked":2,"n_instrument":9,"n_unverified":0,"n_samples":11,"n_pointer_only_licence":6,"sample_list":"/paper/focal-loss-for-dense-object-detection#ran","syntology_url":"https://syntology.ai/paper/1708.02002","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1708.02002"}}}},{"rank_in_archive_order":209,"model":"Cascade R-CNN (ResNet-101-FPN+)","metrics":{"AP50":"61.1","AP75":"41.9","APL":"49.8","APM":"41.8","APS":"21.3","Hardware Burden":"3G","box mAP":"38.8"},"uses_additional_data":false,"paper_date":"2017-12-03","paper":"/paper/cascade-r-cnn-delving-into-high-quality","paper_url":"http://arxiv.org/abs/1712.00726v1","paper_title":"Cascade R-CNN: Delving into High Quality Object Detection","code":"https://github.com/open-mmlab/mmdetection","n_code_links":8,"official":{"repos":["zhaoweicai/cascade-rcnn"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2,"sample_list":"/paper/cascade-r-cnn-delving-into-high-quality#ran","syntology_url":"https://syntology.ai/paper/1712.00726","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1712.00726"}}}},{"rank_in_archive_order":210,"model":"M2Det (ResNet-101, single-scale)","metrics":{"AP50":"59.4","AP75":"41.7","APL":"53.4","APM":"43.9","APS":"20.5","Hardware Burden":"27G","box mAP":"38.8"},"uses_additional_data":false,"paper_date":"2018-11-12","paper":"/paper/m2det-a-single-shot-object-detector-based-on","paper_url":"http://arxiv.org/abs/1811.04533v3","paper_title":"M2Det: A Single-Shot Object Detector based on Multi-Level Feature Pyramid Network","code":"https://github.com/LeeDongYeun/keras-m2det","n_code_links":11,"official":null,"syntology":{"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0,"sample_list":"/paper/m2det-a-single-shot-object-detector-based-on#ran","syntology_url":"https://syntology.ai/paper/1811.04533","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.04533"}}}},{"rank_in_archive_order":211,"model":"SaccadeNet (DLA-34-DCN)","metrics":{"AP50":"55.6","AP75":"41.4","APL":"50.6","APM":"42.1","APS":"19.2","Hardware Burden":"46G","box mAP":"38.5"},"uses_additional_data":false,"paper_date":"2020-03-26","paper":"/paper/saccadenet-a-fast-and-accurate-object","paper_url":"https://arxiv.org/abs/2003.12125v1","paper_title":"SaccadeNet: A Fast and Accurate Object Detector","code":"https://github.com/voidrank/SaccadeNet","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":212,"model":"Mask R-CNN (ResNet-101-FPN)","metrics":{"AP50":"60.3","AP75":"41.7","APL":"50.2","APM":"41.1","APS":"20.1","Hardware Burden":"9G","box mAP":"38.2"},"uses_additional_data":false,"paper_date":"2017-03-20","paper":"/paper/mask-r-cnn","paper_url":"http://arxiv.org/abs/1703.06870v3","paper_title":"Mask R-CNN","code":"https://github.com/tensorflow/models/tree/master/official/vision","n_code_links":179,"official":null,"syntology":{"n_ran":101,"n_constructed":3,"n_ran_checked":77,"n_instrument":24,"n_unverified":39,"n_samples":140,"n_pointer_only_licence":32,"sample_list":"/paper/mask-r-cnn#ran","syntology_url":"https://syntology.ai/paper/1703.06870","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1703.06870"}}}},{"rank_in_archive_order":213,"model":"LeYOLO (Small@640)","metrics":{"GFLOPs":"4.51","Params (M)":"1.9","box mAP":"38.2"},"uses_additional_data":false,"paper_date":"2024-06-20","paper":"/paper/leyolo-new-scalable-and-efficient-cnn","paper_url":"https://arxiv.org/abs/2406.14239v1","paper_title":"LeYOLO, New Scalable and Efficient CNN Architecture for Object Detection","code":"https://github.com/LilianHollard/LeYOLO","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":214,"model":"WSMA-Seg","metrics":{"box mAP":"38.1"},"uses_additional_data":false,"paper_date":"2019-04-30","paper":"/paper/segmentation-is-all-you-need","paper_url":"https://arxiv.org/abs/1904.13300v3","paper_title":"Segmentation is All You Need","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":215,"model":"Faster R-CNN + FPN + CGD","metrics":{"box mAP":"37.9"},"uses_additional_data":false,"paper_date":"2019-07-23","paper":"/paper/compact-global-descriptor-for-neural-networks","paper_url":"https://arxiv.org/abs/1907.09665v10","paper_title":"Compact Global Descriptor for Neural Networks","code":"https://github.com/HolmesShuan/Compact-Global-Descriptor","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":216,"model":"CornerNet511 (Hourglass-52, single-scale)","metrics":{"AP50":"53.7","AP75":"40.1","APL":"50.5","APM":"39.0","APS":"17.0","box mAP":"37.8"},"uses_additional_data":false,"paper_date":"2018-08-03","paper":"/paper/cornernet-detecting-objects-as-paired","paper_url":"http://arxiv.org/abs/1808.01244v2","paper_title":"CornerNet: Detecting Objects as Paired Keypoints","code":"https://github.com/open-mmlab/mmdetection","n_code_links":5,"official":{"repos":["princeton-vl/CornerNet"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":8,"ran_from_kinds":["official"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":8,"n_samples":11,"n_pointer_only_licence":2,"sample_list":"/paper/cornernet-detecting-objects-as-paired#ran","syntology_url":"https://syntology.ai/paper/1808.01244","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1808.01244"}}}},{"rank_in_archive_order":217,"model":"RefineDet512+ (VGG-16)","metrics":{"AP50":"58.7","AP75":"40.8","APL":"48.3","APM":"40.3","APS":"22.7","box mAP":"37.6"},"uses_additional_data":false,"paper_date":"2017-11-18","paper":"/paper/single-shot-refinement-neural-network-for","paper_url":"http://arxiv.org/abs/1711.06897v3","paper_title":"Single-Shot Refinement Neural Network for Object Detection","code":"https://github.com/sfzhang15/RefineDet","n_code_links":16,"official":null,"syntology":null},{"rank_in_archive_order":218,"model":"DeformConv-R-FCN (Aligned-Inception-ResNet)","metrics":{"AP50":"58.0","APL":"52.5","APM":"40.1","APS":"19.4","box mAP":"37.5"},"uses_additional_data":false,"paper_date":"2017-03-17","paper":"/paper/deformable-convolutional-networks","paper_url":"http://arxiv.org/abs/1703.06211v3","paper_title":"Deformable Convolutional Networks","code":"https://github.com/open-mmlab/mmdetection","n_code_links":38,"official":{"repos":["msracver/Deformable-ConvNets"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":6,"n_constructed":0,"n_ran_checked":4,"n_instrument":2,"n_unverified":3,"n_samples":9,"n_pointer_only_licence":4,"sample_list":"/paper/deformable-convolutional-networks#ran","syntology_url":"https://syntology.ai/paper/1703.06211","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1703.06211"}}}},{"rank_in_archive_order":219,"model":"Faster R-CNN (ImageNet+300M)","metrics":{"AP50":"58","AP75":"40.1","APL":"51.2","APM":"41.1","APS":"17.5","box mAP":"37.4"},"uses_additional_data":false,"paper_date":"2017-07-10","paper":"/paper/revisiting-unreasonable-effectiveness-of-data","paper_url":"http://arxiv.org/abs/1707.02968v2","paper_title":"Revisiting Unreasonable Effectiveness of Data in Deep Learning Era","code":"https://github.com/Tencent/tencent-ml-images","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":220,"model":"Mask R-CNN (Bottleneck-injected ResNet-50, FPN)","metrics":{"box mAP":"36.9"},"uses_additional_data":false,"paper_date":"2020-11-25","paper":"/paper/torchdistill-a-modular-configuration-driven","paper_url":"https://arxiv.org/abs/2011.12913v2","paper_title":"torchdistill: A Modular, Configuration-Driven Framework for Knowledge Distillation","code":"https://github.com/yoshitomo-matsubara/torchdistill","n_code_links":1,"official":{"repos":["yoshitomo-matsubara/torchdistill"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":16,"ran_from_kinds":["official"]},"syntology":{"n_ran":10,"n_constructed":0,"n_ran_checked":0,"n_instrument":10,"n_unverified":16,"n_samples":26,"n_pointer_only_licence":0,"sample_list":"/paper/torchdistill-a-modular-configuration-driven#ran","syntology_url":"https://syntology.ai/paper/2011.12913","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2011.12913"}}}},{"rank_in_archive_order":221,"model":"Faster R-CNN + TDM","metrics":{"box mAP":"36.8"},"uses_additional_data":false,"paper_date":"2016-12-20","paper":"/paper/beyond-skip-connections-top-down-modulation","paper_url":"http://arxiv.org/abs/1612.06851v2","paper_title":"Beyond Skip Connections: Top-Down Modulation for Object Detection","code":"https://github.com/MTCloudVision/mxnet-dssd","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":222,"model":"Cascade R-CNN (ResNet-50-FPN+)","metrics":{"AP50":"59","AP75":"39.2","APL":"46.4","APM":"38.8","APS":"20.3","Hardware Burden":"3G","box mAP":"36.5"},"uses_additional_data":false,"paper_date":"2017-12-03","paper":"/paper/cascade-r-cnn-delving-into-high-quality","paper_url":"http://arxiv.org/abs/1712.00726v1","paper_title":"Cascade R-CNN: Delving into High Quality Object Detection","code":"https://github.com/open-mmlab/mmdetection","n_code_links":8,"official":{"repos":["zhaoweicai/cascade-rcnn"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2,"sample_list":"/paper/cascade-r-cnn-delving-into-high-quality#ran","syntology_url":"https://syntology.ai/paper/1712.00726","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1712.00726"}}}},{"rank_in_archive_order":223,"model":"RefineDet512 (ResNet-101)","metrics":{"AP50":"57.5","AP75":"39.5","APL":"51.4","APM":"39.9","APS":"16.6","box mAP":"36.4"},"uses_additional_data":false,"paper_date":"2017-11-18","paper":"/paper/single-shot-refinement-neural-network-for","paper_url":"http://arxiv.org/abs/1711.06897v3","paper_title":"Single-Shot Refinement Neural Network for Object Detection","code":"https://github.com/sfzhang15/RefineDet","n_code_links":16,"official":null,"syntology":null},{"rank_in_archive_order":224,"model":"Faster R-CNN + FPN","metrics":{"Hardware Burden":"2G","box mAP":"36.2"},"uses_additional_data":true,"paper_date":"2016-12-09","paper":"/paper/feature-pyramid-networks-for-object-detection","paper_url":"http://arxiv.org/abs/1612.03144v2","paper_title":"Feature Pyramid Networks for Object Detection","code":"https://github.com/PaddlePaddle/PaddleOCR","n_code_links":85,"official":null,"syntology":{"n_ran":33,"n_constructed":9,"n_ran_checked":28,"n_instrument":5,"n_unverified":18,"n_samples":51,"n_pointer_only_licence":11,"sample_list":"/paper/feature-pyramid-networks-for-object-detection#ran","syntology_url":"https://syntology.ai/paper/1612.03144","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1612.03144"}}}},{"rank_in_archive_order":225,"model":"Faster R-CNN (Bottleneck-injected ResNet-50 and FPN)","metrics":{"box mAP":"35.9"},"uses_additional_data":false,"paper_date":"2020-11-25","paper":"/paper/torchdistill-a-modular-configuration-driven","paper_url":"https://arxiv.org/abs/2011.12913v2","paper_title":"torchdistill: A Modular, Configuration-Driven Framework for Knowledge Distillation","code":"https://github.com/yoshitomo-matsubara/torchdistill","n_code_links":1,"official":{"repos":["yoshitomo-matsubara/torchdistill"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":16,"ran_from_kinds":["official"]},"syntology":{"n_ran":10,"n_constructed":0,"n_ran_checked":0,"n_instrument":10,"n_unverified":16,"n_samples":26,"n_pointer_only_licence":0,"sample_list":"/paper/torchdistill-a-modular-configuration-driven#ran","syntology_url":"https://syntology.ai/paper/2011.12913","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2011.12913"}}}}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"adjudicator":"Claude Opus 5.5","adjudicator_from":"groundwork/59_code_with_papers/LB_EXTRACTOR_PREREG.md (not recorded in lb_measurement.json; the file's frozen_commit, measured_on and counts equal the run the pre-registration records)","adjudicator_sensitivity":[69,70],"adjudicator_specificity":[101,103],"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication by a model (adjudicator) of accepted entries on a held-out split of archive papers, rules frozen before the test; adjudicator_sensitivity and adjudicator_specificity are its own controls as [judged right, of]; it was not measured on the newer papers placed here","measurement_sentence":"Measured before publishing, on held-out archive papers: the extractor was given 883 of them and produced output for 881 (the other 2 had no title and were excluded before any model call, so they are not part of this measurement). A model adjudicator (Claude Opus 5.5), blind to which entries were real, judged 108 of 110 accepted entries correct on those held-out archive papers; its own controls: 69 of 70 archive-confirmed entries judged true, 101 of 103 corrupted copies judged false. It was not measured on the newer papers whose results are placed on this site.","coverage":{"sentence":"Syntology has checked 8,886 of the 18,637 papers on this site that are newer than the archive (for 3,717 of them no archive leaderboard matched the paper's tables, so there was nothing further to check); 733 were read and have nothing to place (arXiv has no HTML version of the paper, or that version has no tables), 41 could not be read (the extractor's reply could not be parsed), and results from the other 8,977 appear after they are checked.","complete":false,"papers_newer_than_archive":18637,"papers_checked":8886,"papers_checked_no_leaderboard_matched":3717,"papers_read_nothing_to_place":733,"papers_could_not_be_read":41,"papers_could_not_be_read_by_status":{"unparseable":41},"papers_extracted_not_yet_verified":0,"boards_without_verdict":3,"papers_not_yet_extracted":8975},"board_status":{"sentence":"Of the 8,888 newer papers whose tables Syntology has read (8,886 checked in full and 2 with a leaderboard still awaiting a verdict), 5 had this board among the leaderboards the extractor considered for their tables (it keeps at most 10 boards per paper and 4 per dataset; the lists of 1,592 of the 8,888 were already full without this board, so if it was crowded out of them it is not counted), and none proposed a result, so none await a verdict and none were placed.","note":"papers, from the extractor's own records, over the newer papers whose tables were read; proposed = no_cell_passed_checks + rejected_by_independent_check + accepted_not_placed + awaiting_verdict + placed; counts, never a rate","eligible":true,"eligible_note":"false when the extractor never considers this board: it loads only boards with archive rows and at least one metric column (lb_extract.py Boards), so no newer paper can be proposed here; archive_rows and metric_columns say which","archive_rows":225,"metric_columns":10,"papers_read":8888,"papers_read_checked":8886,"papers_read_awaiting_verdict":2,"papers_read_verified":8888,"papers_read_not_yet_verified":0,"papers_read_at_candidate_cap":1596,"papers_read_list_full_without_this_board":1592,"candidates":5,"candidates_capped_note":"candidates = papers that had this board among the leaderboards the extractor considered for their tables; the extractor keeps at most 10 per paper and 4 per dataset, so a board crowded out of a paper's list is not counted and candidates is a floor; papers_read_list_full_without_this_board counts the read papers whose list did not hold this board and had reached 10, or held 4 boards of this board's dataset (the only papers that could have crowded it out); papers_read_at_candidate_cap counts, over every board, the papers whose list reached 10","proposed":0,"no_cell_passed_checks":0,"rejected_by_independent_check":0,"accepted_not_placed":0,"awaiting_verdict":0,"placed":0,"placed_entries_listed":0,"file_lines_unreadable_as_read":0,"since_line":"Since the archive (Syntology): none placed; no newer paper judged to report on this board so far"},"judged_to_report":{"heading":"Newer papers whose tables a model judged to report on this benchmark (a model's judgement, not a result; newest first by arXiv id)","judged_by":{"model":"a model","models_as_recorded":[],"a_record_without_a_model":false,"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here","order":"newest first by arXiv id (the identifier's order, not a rank)","outcomes":{"placed":"placed","no_cell_passed_checks":"no cell passed the extractor's checks","refused_by_rule":"refused by a rule","rejected":"rejected by the independent check","accepted_not_placed":"accepted by the independent check but not placed by this site","awaiting":"awaiting a verdict"},"reason_note":"for refused_by_rule, the rules' plain words for the reason codes the record gives (never the quoted or the actual cell text); null for every other outcome","total":0,"shown_on_page":0,"no_cell_split":{"no_cell_passed_checks_in_ledger":0,"rows_refused_by_rule":0,"rows_no_cell_passed_checks":0},"rows":[]},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per row: of M harvested code samples from that row's paper, n_ran executed on a synthesized fixture (n_ran = n_ran_checked + n_instrument; n_instrument counts failures of Syntology's instrument, not of the code); the other M - n_ran are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"rows_with_graph_line":131,"rows_with_any_sample_ran":128,"rows_with_a_run_with_no_instrument_failure":109,"official":{"state_rule":"the archive's official repositories have samples for this paper that ran: 'official (archive's flag): N ran' (N counts them, instrument failures included); they have samples, none ran: 'official: harvested, nothing ran'; they have no sample for this paper and another sample ran: 'community repositories only' when every sample that ran came from a repository the archive lists for the paper but neither marks official nor records as mentioned in it, or one Syntology harvested outside the archive's links, else 'official: no sample here; runs from other or unrecorded repositories' (a repository named in the paper or found in its text by Syntology, or no repository recorded); otherwise 'official: harvested for another paper' or 'official: not harvested'. Absent when the archive marks no repository official. Official is the archive's is_official flag, not an authorship verdict","flag":"the archive's is_official flag for the paper's code link; not a verdict on who wrote the code","rows_with_an_archive_official_repository":106,"rows_whose_official_repository_has_a_sample_that_ran":50,"rows_whose_official_repository_has_a_run_with_no_instrument_failure":42,"rows_community_repositories_only":34,"rows_runs_from_other_or_unrecorded_repositories":13,"note":"rows[].official, per row with a graph line: repos (marked official in the archive), state, n_ran and n_unverified (samples from those repositories), and ran_from_kinds (the kinds of repository the paper's samples that ran came from; 'unlocated' is no repository recorded)"},"filters":{"ran_modes":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"the page's filters hide rows and never renumber them; they read the Ran cell's counts, the same figures rows[].syntology and rows[].official carry"},"row_route":"rows[].syntology carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers","distinct_papers_with_graph_line":72,"distinct_papers_with_any_sample_ran":70,"distinct_papers_with_a_run_with_no_instrument_failure":60,"samples_over_distinct_papers":{"n_ran":1003,"n_constructed":89,"n_ran_checked":766,"n_instrument":237,"n_unverified":451,"n_samples":1454,"n_pointer_only_licence":295,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":1740,"n_constructed":163,"n_ran_checked":1304,"n_instrument":436,"n_unverified":729,"n_samples":2469,"n_pointer_only_licence":584,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}},"record_sha256":"bd7421b7cca6165f47a602e008984e09cfa96d73e60437946c0ed89b517ce7b4","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}