{"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-minival","task":{"name":"Object Detection","url":"/task/object-detection","note":null},"dataset":{"name":"COCO minival","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 AP","AP50","AP75","APS","APM","APL","Params (M)"],"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 AP":"higher","AP50":null,"AP75":null,"APS":null,"APM":null,"APL":null,"Params (M)":"lower"}},"counts":{"rows":220,"rows_with_code":217,"rows_with_paper_page":220,"rows_dated":220,"rows_using_additional_data":25},"rows":[{"rank_in_archive_order":1,"model":"PE_spatial (DETA)","metrics":{"Params (M)":"1900","box AP":"66.0"},"uses_additional_data":true,"paper_date":"2025-04-17","paper":"/paper/perception-encoder-the-best-visual-embeddings","paper_url":"https://arxiv.org/abs/2504.13181v1","paper_title":"Perception Encoder: The best visual embeddings are not at the output of the network","code":"https://github.com/facebookresearch/perception_models","n_code_links":1,"official":null,"syntology":{"n_ran":14,"n_constructed":0,"n_ran_checked":6,"n_instrument":8,"n_unverified":4,"n_samples":18,"n_pointer_only_licence":2,"sample_list":"/paper/perception-encoder-the-best-visual-embeddings#ran","syntology_url":"https://syntology.ai/paper/2504.13181","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.13181"}}}},{"rank_in_archive_order":2,"model":"Co-DETR","metrics":{"Params (M)":"314","box AP":"65.9"},"uses_additional_data":true,"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":3,"model":"M3I Pre-training (InternImage-H)","metrics":{"box AP":"65.0"},"uses_additional_data":true,"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":"InternImage-H","metrics":{"box AP":"65.0"},"uses_additional_data":true,"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":5,"model":"Co-DETR (Swin-L)","metrics":{"Params (M)":"218","box AP":"64.7"},"uses_additional_data":true,"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":6,"model":"Focal-Stable-DINO (Focal-Huge, no TTA)","metrics":{"AP50":"81.5","AP75":"71.4","APL":"78.5","APM":"68.5","APS":"50.4","Params (M)":"689","box AP":"64.6"},"uses_additional_data":true,"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":7,"model":"EVA","metrics":{"AP50":"82.1","AP75":"70.8","APL":"78.5","APM":"68.4","APS":"49.4","box AP":"64.5"},"uses_additional_data":true,"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":"ViT-CoMer","metrics":{"Params (M)":"363","box AP":"64.3"},"uses_additional_data":false,"paper_date":"2024-03-13","paper":"/paper/vit-comer-vision-transformer-with","paper_url":"https://openreview.net/forum?id=srPMwpkWbR&invitationId=thecvf.com/CVPR/2024/Conference/Submission1221/-/Camera_Ready_Revision&referrer=%5BAuthor%20Console%5D(%2Fgroup%3Fid%3Dthecvf.com%2FCVPR%2F2024%2FConference%2FAuthors%23author-tasks)","paper_title":"ViT-CoMer: Vision Transformer with Convolutional Multi-scale Feature Interaction for Dense Predictions","code":"https://github.com/Traffic-X/ViT-CoMer","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":9,"model":"FocalNet-H (DINO)","metrics":{"box AP":"64.2"},"uses_additional_data":true,"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":{"box AP":"64.2"},"uses_additional_data":true,"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":"CP-DETR-L Swin-L(Fine tuning separately in COCO)","metrics":{"box AP":"64.1"},"uses_additional_data":true,"paper_date":"2024-12-13","paper":"/paper/cp-detr-concept-prompt-guide-detr-toward","paper_url":"https://arxiv.org/abs/2412.09799v1","paper_title":"CP-DETR: Concept Prompt Guide DETR Toward Stronger Universal Object Detection","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":12,"model":"RevCol-H(DINO)","metrics":{"box AP":"63.8"},"uses_additional_data":true,"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":13,"model":"DINO (Swin-L)","metrics":{"box AP":"63.2"},"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":14,"model":"Grounding DINO","metrics":{"box AP":"63.0"},"uses_additional_data":true,"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":15,"model":"SwinV2-G (HTC++)","metrics":{"box AP":"62.5"},"uses_additional_data":true,"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":16,"model":"Florence-CoSwin-H","metrics":{"box AP":"62"},"uses_additional_data":true,"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":17,"model":"GLEE-Pro","metrics":{"box AP":"62.0"},"uses_additional_data":true,"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":18,"model":"ViTDet, ViT-H Cascade (multiscale)","metrics":{"box AP":"61.3"},"uses_additional_data":false,"paper_date":"2022-03-30","paper":"/paper/exploring-plain-vision-transformer-backbones","paper_url":"https://arxiv.org/abs/2203.16527v2","paper_title":"Exploring Plain Vision Transformer Backbones for Object Detection","code":"https://github.com/facebookresearch/detectron2/tree/main/projects/ViTDet","n_code_links":11,"official":{"repos":["facebookresearch/detectron2"],"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":1,"n_samples":4,"n_pointer_only_licence":1,"sample_list":"/paper/exploring-plain-vision-transformer-backbones#ran","syntology_url":"https://syntology.ai/paper/2203.16527","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.16527"}}}},{"rank_in_archive_order":19,"model":"GLIP (Swin-L, multi-scale)","metrics":{"box AP":"60.8"},"uses_additional_data":true,"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":20,"model":"Soft Teacher + Swin-L (HTC++, multi-scale)","metrics":{"box AP":"60.7"},"uses_additional_data":true,"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":21,"model":"UNINEXT-H","metrics":{"AP50":"77.5","AP75":"66.7","APL":"75.3","APM":"64.8","APS":"45.1","box AP":"60.6"},"uses_additional_data":true,"paper_date":"2023-03-12","paper":"/paper/universal-instance-perception-as-object","paper_url":"https://arxiv.org/abs/2303.06674v2","paper_title":"Universal Instance Perception as Object Discovery and Retrieval","code":"https://github.com/MasterBin-IIAU/UNINEXT","n_code_links":1,"official":{"repos":["MasterBin-IIAU/UNINEXT"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]},"syntology":{"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":0,"n_samples":4,"n_pointer_only_licence":2,"sample_list":"/paper/universal-instance-perception-as-object#ran","syntology_url":"https://syntology.ai/paper/2303.06674","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.06674"}}}},{"rank_in_archive_order":22,"model":"ViT-Adapter-L (HTC++, BEiTv2 pretrain, multi-scale)","metrics":{"box AP":"60.5"},"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":23,"model":"ViTDet, ViT-H Cascade","metrics":{"box AP":"60.4"},"uses_additional_data":false,"paper_date":"2022-03-30","paper":"/paper/exploring-plain-vision-transformer-backbones","paper_url":"https://arxiv.org/abs/2203.16527v2","paper_title":"Exploring Plain Vision Transformer Backbones for Object Detection","code":"https://github.com/facebookresearch/detectron2/tree/main/projects/ViTDet","n_code_links":11,"official":{"repos":["facebookresearch/detectron2"],"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":1,"n_samples":4,"n_pointer_only_licence":1,"sample_list":"/paper/exploring-plain-vision-transformer-backbones#ran","syntology_url":"https://syntology.ai/paper/2203.16527","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.16527"}}}},{"rank_in_archive_order":24,"model":"GLEE-Plus","metrics":{"box AP":"60.4"},"uses_additional_data":true,"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":25,"model":"DyHead (Swin-L, multi scale, self-training)","metrics":{"AP50":"78.2","APL":"74.2","box AP":"60.3"},"uses_additional_data":true,"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":26,"model":"ViT-Adapter-L (HTC++, BEiT pretrain, multi-scale)","metrics":{"box AP":"60.2"},"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":27,"model":"Soft Teacher+Swin-L(HTC++, single scale)","metrics":{"box AP":"60.1"},"uses_additional_data":true,"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":28,"model":"CBNetV2 (Dual-Swin-L HTC, multi-scale)","metrics":{"box AP":"59.6"},"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":29,"model":"Frozen Backbone, SwinV2-G-ext22K (HTC)","metrics":{"box AP":"59.3"},"uses_additional_data":false,"paper_date":"2022-11-03","paper":"/paper/could-giant-pretrained-image-models-extract","paper_url":"https://arxiv.org/abs/2211.02043v1","paper_title":"Could Giant Pretrained Image Models Extract Universal Representations?","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":30,"model":"HorNet-L","metrics":{"box AP":"59.2"},"uses_additional_data":false,"paper_date":"2022-07-28","paper":"/paper/hornet-efficient-high-order-spatial","paper_url":"https://arxiv.org/abs/2207.14284v3","paper_title":"HorNet: Efficient High-Order Spatial Interactions with Recursive Gated Convolutions","code":"https://github.com/open-mmlab/mmclassification","n_code_links":8,"official":{"repos":["raoyongming/hornet"],"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/hornet-efficient-high-order-spatial#ran","syntology_url":"https://syntology.ai/paper/2207.14284","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.14284"}}}},{"rank_in_archive_order":31,"model":"MOAT-3 (IN-22K pretraining, single-scale)","metrics":{"box AP":"59.2"},"uses_additional_data":false,"paper_date":"2022-10-04","paper":"/paper/moat-alternating-mobile-convolution-and","paper_url":"https://arxiv.org/abs/2210.01820v2","paper_title":"MOAT: Alternating Mobile Convolution and Attention Brings Strong Vision Models","code":"https://github.com/google-research/deeplab2","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":32,"model":"CBNetV2 (Dual-Swin-L HTC, multi-scale)","metrics":{"box AP":"59.1"},"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":33,"model":"Focal-L (DyHead, multi-scale)","metrics":{"AP50":"77.2","APL":"73.4","box AP":"58.7"},"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":"MViTv2-L (Cascade Mask R-CNN, multi-scale, IN21k pre-train)","metrics":{"box AP":"58.7"},"uses_additional_data":false,"paper_date":"2021-12-02","paper":"/paper/improved-multiscale-vision-transformers-for","paper_url":"https://arxiv.org/abs/2112.01526v2","paper_title":"MViTv2: Improved Multiscale Vision Transformers for Classification and Detection","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":9,"official":null,"syntology":null},{"rank_in_archive_order":35,"model":"MOAT-2 (IN-22K pretraining, single-scale)","metrics":{"box AP":"58.5"},"uses_additional_data":false,"paper_date":"2022-10-04","paper":"/paper/moat-alternating-mobile-convolution-and","paper_url":"https://arxiv.org/abs/2210.01820v2","paper_title":"MOAT: Alternating Mobile Convolution and Attention Brings Strong Vision Models","code":"https://github.com/google-research/deeplab2","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":36,"model":"DyHead (Swin-L, multi scale)","metrics":{"AP50":"76.8","APL":"73.2","APM":"62.2","APS":"44.5","box AP":"58.4"},"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":37,"model":"Swin-L (HTC++, multi scale)","metrics":{"box AP":"58"},"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":38,"model":"MOAT-1 (IN-1K pretraining, single-scale)","metrics":{"box AP":"57.7"},"uses_additional_data":false,"paper_date":"2022-10-04","paper":"/paper/moat-alternating-mobile-convolution-and","paper_url":"https://arxiv.org/abs/2210.01820v2","paper_title":"MOAT: Alternating Mobile Convolution and Attention Brings Strong Vision Models","code":"https://github.com/google-research/deeplab2","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":39,"model":"UM-MAE(HTC++, Swin-L, IN1K)","metrics":{"box AP":"57.4"},"uses_additional_data":false,"paper_date":"2022-05-20","paper":"/paper/uniform-masking-enabling-mae-pre-training-for","paper_url":"https://arxiv.org/abs/2205.10063v1","paper_title":"Uniform Masking: Enabling MAE Pre-training for Pyramid-based Vision Transformers with Locality","code":"https://github.com/implus/um-mae","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":40,"model":"YOLOv6-L6(46 fps, 1280, V100)","metrics":{"AP50":"74.5","box AP":"57.2"},"uses_additional_data":false,"paper_date":"2023-01-13","paper":"/paper/yolov6-v3-0-a-full-scale-reloading","paper_url":"https://arxiv.org/abs/2301.05586v1","paper_title":"YOLOv6 v3.0: A Full-Scale Reloading","code":"https://github.com/PaddlePaddle/PaddleDetection","n_code_links":5,"official":{"repos":["meituan/yolov6"],"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":2,"sample_list":"/paper/yolov6-v3-0-a-full-scale-reloading#ran","syntology_url":"https://syntology.ai/paper/2301.05586","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.05586"}}}},{"rank_in_archive_order":41,"model":"Swin-L (HTC++, single scale)","metrics":{"box AP":"57.1"},"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":42,"model":"TransNeXt-Base (IN-1K pretrain, DINO 1x)","metrics":{"box AP":"57.1"},"uses_additional_data":false,"paper_date":"2023-11-28","paper":"/paper/transnext-robust-foveal-visual-perception-for","paper_url":"https://arxiv.org/abs/2311.17132v3","paper_title":"TransNeXt: Robust Foveal Visual Perception for Vision Transformers","code":"https://github.com/Westlake-AI/openmixup","n_code_links":4,"official":{"repos":["daishiresearch/transnext"],"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":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":0,"n_samples":5,"n_pointer_only_licence":0,"sample_list":"/paper/transnext-robust-foveal-visual-perception-for#ran","syntology_url":"https://syntology.ai/paper/2311.17132","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.17132"}}}},{"rank_in_archive_order":43,"model":"Cascade Eff-B7 NAS-FPN (1280, self-training Copy Paste, single-scale)","metrics":{"box AP":"57.0"},"uses_additional_data":true,"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":44,"model":"TransNeXt-Small (IN-1K pretrain, DINO 1x)","metrics":{"box AP":"56.6"},"uses_additional_data":false,"paper_date":"2023-11-28","paper":"/paper/transnext-robust-foveal-visual-perception-for","paper_url":"https://arxiv.org/abs/2311.17132v3","paper_title":"TransNeXt: Robust Foveal Visual Perception for Vision Transformers","code":"https://github.com/Westlake-AI/openmixup","n_code_links":4,"official":{"repos":["daishiresearch/transnext"],"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":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":0,"n_samples":5,"n_pointer_only_licence":0,"sample_list":"/paper/transnext-robust-foveal-visual-perception-for#ran","syntology_url":"https://syntology.ai/paper/2311.17132","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.17132"}}}},{"rank_in_archive_order":45,"model":"QueryInst (single scale)","metrics":{"AP50":"75.8","AP75":"61.7","APL":"71.5","APM":"59.8","APS":"40.2","box AP":"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":46,"model":"MViTv2-H (Cascade Mask R-CNN, single-scale, IN21k pre-train)","metrics":{"box AP":"56.1"},"uses_additional_data":false,"paper_date":"2021-12-02","paper":"/paper/improved-multiscale-vision-transformers-for","paper_url":"https://arxiv.org/abs/2112.01526v2","paper_title":"MViTv2: Improved Multiscale Vision Transformers for Classification and Detection","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":9,"official":null,"syntology":null},{"rank_in_archive_order":47,"model":"MOAT-0 (IN-1K pretraining, single-scale)","metrics":{"box AP":"55.9"},"uses_additional_data":false,"paper_date":"2022-10-04","paper":"/paper/moat-alternating-mobile-convolution-and","paper_url":"https://arxiv.org/abs/2210.01820v2","paper_title":"MOAT: Alternating Mobile Convolution and Attention Brings Strong Vision Models","code":"https://github.com/google-research/deeplab2","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":48,"model":"TransNeXt-Tiny (IN-1K pretrain, DINO 1x)","metrics":{"box AP":"55.7"},"uses_additional_data":false,"paper_date":"2023-11-28","paper":"/paper/transnext-robust-foveal-visual-perception-for","paper_url":"https://arxiv.org/abs/2311.17132v3","paper_title":"TransNeXt: Robust Foveal Visual Perception for Vision Transformers","code":"https://github.com/Westlake-AI/openmixup","n_code_links":4,"official":{"repos":["daishiresearch/transnext"],"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":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":0,"n_samples":5,"n_pointer_only_licence":0,"sample_list":"/paper/transnext-robust-foveal-visual-perception-for#ran","syntology_url":"https://syntology.ai/paper/2311.17132","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.17132"}}}},{"rank_in_archive_order":49,"model":"YOLOv4-P7 CSP-P7 (single-scale, 16 fps)","metrics":{"AP50":"73.3","AP75":"60.7","APL":"67.4","APM":"59.5","APS":"38.1","box AP":"55.4"},"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":50,"model":"tiny-MOAT-3 (IN-1K pretraining, single-scale)","metrics":{"box AP":"55.2"},"uses_additional_data":false,"paper_date":"2022-10-04","paper":"/paper/moat-alternating-mobile-convolution-and","paper_url":"https://arxiv.org/abs/2210.01820v2","paper_title":"MOAT: Alternating Mobile Convolution and Attention Brings Strong Vision Models","code":"https://github.com/google-research/deeplab2","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":51,"model":"FAN-L-Hybrid","metrics":{"box AP":"55.1"},"uses_additional_data":false,"paper_date":"2022-04-26","paper":"/paper/understanding-the-robustness-in-vision","paper_url":"https://arxiv.org/abs/2204.12451v4","paper_title":"Understanding The Robustness in Vision Transformers","code":"https://github.com/nvlabs/fan","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":52,"model":"Hiera-L","metrics":{"box AP":"55"},"uses_additional_data":false,"paper_date":"2023-06-01","paper":"/paper/hiera-a-hierarchical-vision-transformer","paper_url":"https://arxiv.org/abs/2306.00989v1","paper_title":"Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles","code":"https://github.com/huggingface/pytorch-image-models","n_code_links":4,"official":{"repos":["facebookresearch/hiera"],"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":["official"]},"syntology":{"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"n_samples":6,"n_pointer_only_licence":0,"sample_list":"/paper/hiera-a-hierarchical-vision-transformer#ran","syntology_url":"https://syntology.ai/paper/2306.00989","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.00989"}}}},{"rank_in_archive_order":53,"model":"GLEE-Lite","metrics":{"box AP":"55.0"},"uses_additional_data":true,"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":54,"model":"TEC(VIT-B, Mask-RCNN)","metrics":{"box AP":"54.6"},"uses_additional_data":false,"paper_date":"2022-10-20","paper":"/paper/towards-sustainable-self-supervised-learning","paper_url":"https://arxiv.org/abs/2210.11016v1","paper_title":"Towards Sustainable Self-supervised Learning","code":"https://github.com/sail-sg/tec","n_code_links":1,"official":{"repos":["sail-sg/tec"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":6,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]},"syntology":{"n_ran":6,"n_constructed":6,"n_ran_checked":6,"n_instrument":0,"n_unverified":2,"n_samples":8,"n_pointer_only_licence":8,"sample_list":"/paper/towards-sustainable-self-supervised-learning#ran","syntology_url":"https://syntology.ai/paper/2210.11016","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.11016"}}}},{"rank_in_archive_order":55,"model":"Cascade Eff-B7 NAS-FPN (1280)","metrics":{"box AP":"54.5"},"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":56,"model":"CAE (ViT-L, Mask R-CNN, 1x schedule)","metrics":{"box AP":"54.5"},"uses_additional_data":false,"paper_date":"2022-02-07","paper":"/paper/context-autoencoder-for-self-supervised","paper_url":"https://arxiv.org/abs/2202.03026v3","paper_title":"Context Autoencoder for Self-Supervised Representation Learning","code":"https://github.com/open-mmlab/mmselfsup","n_code_links":6,"official":null,"syntology":null},{"rank_in_archive_order":57,"model":"MViTv2-L (Cascade Mask R-CNN, single-scale)","metrics":{"box AP":"54.3"},"uses_additional_data":false,"paper_date":"2021-12-02","paper":"/paper/improved-multiscale-vision-transformers-for","paper_url":"https://arxiv.org/abs/2112.01526v2","paper_title":"MViTv2: Improved Multiscale Vision Transformers for Classification and Detection","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":9,"official":null,"syntology":null},{"rank_in_archive_order":58,"model":"SpineNet-190 (1280, with Self-training on OpenImages, single-scale)","metrics":{"box AP":"54.2"},"uses_additional_data":true,"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":59,"model":"Cascade RCNN-RS (SpineNet-143L, single scale)","metrics":{"APL":"70.6","APM":"56.7","APS":"34.5","box AP":"53.6"},"uses_additional_data":false,"paper_date":"2021-06-30","paper":"/paper/simple-training-strategies-and-model-scaling","paper_url":"https://arxiv.org/abs/2107.00057v1","paper_title":"Simple Training Strategies and Model Scaling for Object Detection","code":"https://github.com/tensorflow/tpu","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":60,"model":"UniverseNet-20.08d (Res2Net-101, DCN, multi-scale)","metrics":{"AP50":"70.8","AP75":"58.9","APL":"68.1","APM":"57.5","APS":"36.9","box AP":"53.5"},"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":61,"model":"MAE (ViT-L, Mask R-CNN)","metrics":{"box AP":"53.3"},"uses_additional_data":false,"paper_date":"2021-11-11","paper":"/paper/masked-autoencoders-are-scalable-vision","paper_url":"https://arxiv.org/abs/2111.06377v2","paper_title":"Masked Autoencoders Are Scalable Vision Learners","code":"https://github.com/facebookresearch/mae","n_code_links":58,"official":{"repos":["facebookresearch/mae"],"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":86,"n_constructed":40,"n_ran_checked":68,"n_instrument":18,"n_unverified":51,"n_samples":137,"n_pointer_only_licence":78,"sample_list":"/paper/masked-autoencoders-are-scalable-vision#ran","syntology_url":"https://syntology.ai/paper/2111.06377","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.06377"}}}},{"rank_in_archive_order":62,"model":"Cascade RCNN-RS (ResNet-200, single scale)","metrics":{"APL":"70.3","APM":"56.2","APS":"33.9","box AP":"53.1"},"uses_additional_data":false,"paper_date":"2021-06-30","paper":"/paper/simple-training-strategies-and-model-scaling","paper_url":"https://arxiv.org/abs/2107.00057v1","paper_title":"Simple Training Strategies and Model Scaling for Object Detection","code":"https://github.com/tensorflow/tpu","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":63,"model":"tiny-MOAT-2 (IN-1K pretraining, single-scale)","metrics":{"box AP":"53.0"},"uses_additional_data":false,"paper_date":"2022-10-04","paper":"/paper/moat-alternating-mobile-convolution-and","paper_url":"https://arxiv.org/abs/2210.01820v2","paper_title":"MOAT: Alternating Mobile Convolution and Attention Brings Strong Vision Models","code":"https://github.com/google-research/deeplab2","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":64,"model":"MViT-L (Mask R-CNN, single-scale, IN21k pre-train)","metrics":{"box AP":"52.7"},"uses_additional_data":false,"paper_date":"2021-12-02","paper":"/paper/improved-multiscale-vision-transformers-for","paper_url":"https://arxiv.org/abs/2112.01526v2","paper_title":"MViTv2: Improved Multiscale Vision Transformers for Classification and Detection","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":9,"official":null,"syntology":null},{"rank_in_archive_order":65,"model":"ResNeSt-200 (multi-scale)","metrics":{"AP50":"71.00","AP75":"57.07","APL":"66.29","APM":"56.36","APS":"36.80","box AP":"52.47"},"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":66,"model":"ActiveMLP-B (Cascade Mask R-CNN)","metrics":{"box AP":"52.3"},"uses_additional_data":false,"paper_date":"2022-03-11","paper":"/paper/activemlp-an-mlp-like-architecture-with","paper_url":"https://arxiv.org/abs/2203.06108v2","paper_title":"Active Token Mixer","code":"https://github.com/microsoft/TokenMixers","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":67,"model":"RetinaNet (SpineNet-190, 1536x1536)","metrics":{"box AP":"52.2"},"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":68,"model":"EfficientDet-D7 (1536)","metrics":{"box AP":"52.1"},"uses_additional_data":false,"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":69,"model":"tiny-MOAT-1 (IN-1K pretraining, single-scale)","metrics":{"box AP":"51.9"},"uses_additional_data":false,"paper_date":"2022-10-04","paper":"/paper/moat-alternating-mobile-convolution-and","paper_url":"https://arxiv.org/abs/2210.01820v2","paper_title":"MOAT: Alternating Mobile Convolution and Attention Brings Strong Vision Models","code":"https://github.com/google-research/deeplab2","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":70,"model":"GCNet (ResNeXt-101 + DCN + cascade + GC r4)","metrics":{"AP50":"70.4","AP75":"56.1","box AP":"51.8"},"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":71,"model":"ELSA-S (Cascade Mask RCNN)","metrics":{"AP50":"70.5","AP75":"56.0","box AP":"51.6"},"uses_additional_data":false,"paper_date":"2021-12-23","paper":"/paper/elsa-enhanced-local-self-attention-for-vision","paper_url":"https://arxiv.org/abs/2112.12786v1","paper_title":"ELSA: Enhanced Local Self-Attention for Vision Transformer","code":"https://github.com/damo-cv/elsa","n_code_links":1,"official":{"repos":["damo-cv/elsa"],"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":0,"sample_list":"/paper/elsa-enhanced-local-self-attention-for-vision#ran","syntology_url":"https://syntology.ai/paper/2112.12786","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.12786"}}}},{"rank_in_archive_order":72,"model":"FocalNet-T (LRF, Cascade Mask R-CNN)","metrics":{"AP50":"70.3","AP75":"56.0","box AP":"51.5"},"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":73,"model":"DINO-5scale (24 epoch)","metrics":{"AP50":"69.1","AP75":"56","APL":"65.8","APM":"54.2","APS":"34.5","box AP":"51.3"},"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":74,"model":"DINO-5scale (36 epoch)","metrics":{"AP50":"69","AP75":"55.8","APL":"65.3","APM":"54.3","APS":"35","box AP":"51.2"},"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":75,"model":"ResNeSt-200-DCN (single-scale)","metrics":{"AP50":"69.53","AP75":"55.40","APL":"65.83","APM":"54.66","APS":"32.67","box AP":"50.91"},"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":76,"model":"UniverseNet-20.08d (Res2Net-101, DCN, single-scale)","metrics":{"AP50":"69.5","AP75":"55.4","APL":"65.8","APM":"55.5","APS":"33.5","box AP":"50.9"},"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":77,"model":"ResNeSt-200 (single-scale)","metrics":{"AP50":"68.78","AP75":"55.17","APL":"63.9","APM":"54.2","box AP":"50.54"},"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":78,"model":"tiny-MOAT-0 (IN-1K pretraining, single-scale)","metrics":{"box AP":"50.5"},"uses_additional_data":false,"paper_date":"2022-10-04","paper":"/paper/moat-alternating-mobile-convolution-and","paper_url":"https://arxiv.org/abs/2210.01820v2","paper_title":"MOAT: Alternating Mobile Convolution and Attention Brings Strong Vision Models","code":"https://github.com/google-research/deeplab2","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":79,"model":"MAE (ViT-B, Mask R-CNN)","metrics":{"box AP":"50.3"},"uses_additional_data":false,"paper_date":"2021-11-11","paper":"/paper/masked-autoencoders-are-scalable-vision","paper_url":"https://arxiv.org/abs/2111.06377v2","paper_title":"Masked Autoencoders Are Scalable Vision Learners","code":"https://github.com/facebookresearch/mae","n_code_links":58,"official":{"repos":["facebookresearch/mae"],"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":86,"n_constructed":40,"n_ran_checked":68,"n_instrument":18,"n_unverified":51,"n_samples":137,"n_pointer_only_licence":78,"sample_list":"/paper/masked-autoencoders-are-scalable-vision#ran","syntology_url":"https://syntology.ai/paper/2111.06377","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.06377"}}}},{"rank_in_archive_order":80,"model":"Sparse R-CNN (PVTv2-B2)","metrics":{"AP50":"69.5","AP75":"54.9","box AP":"50.1"},"uses_additional_data":false,"paper_date":"2021-06-25","paper":"/paper/pvtv2-improved-baselines-with-pyramid-vision","paper_url":"https://arxiv.org/abs/2106.13797v7","paper_title":"PVT v2: Improved Baselines with Pyramid Vision Transformer","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":18,"official":null,"syntology":null},{"rank_in_archive_order":81,"model":"Pix2seq (ViT-L)","metrics":{"box AP":"50.0"},"uses_additional_data":true,"paper_date":"2021-09-22","paper":"/paper/pix2seq-a-language-modeling-framework-for","paper_url":"https://arxiv.org/abs/2109.10852v2","paper_title":"Pix2seq: A Language Modeling Framework for Object Detection","code":"https://github.com/google-research/pix2seq","n_code_links":6,"official":{"repos":["google-research/pix2seq"],"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":3,"n_ran_checked":6,"n_instrument":4,"n_unverified":2,"n_samples":12,"n_pointer_only_licence":10,"sample_list":"/paper/pix2seq-a-language-modeling-framework-for#ran","syntology_url":"https://syntology.ai/paper/2109.10852","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.10852"}}}},{"rank_in_archive_order":82,"model":"DaViT-T (Mask R-CNN, 36 epochs)","metrics":{"box AP":"49.9"},"uses_additional_data":false,"paper_date":"2022-04-07","paper":"/paper/davit-dual-attention-vision-transformers","paper_url":"https://arxiv.org/abs/2204.03645v1","paper_title":"DaViT: Dual Attention Vision Transformers","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":4,"official":{"repos":["dingmyu/davit"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":5,"n_ran_no_instrument_failure":6,"n_unverified":7,"ran_from_kinds":["official"]},"syntology":{"n_ran":8,"n_constructed":5,"n_ran_checked":6,"n_instrument":2,"n_unverified":7,"n_samples":15,"n_pointer_only_licence":0,"sample_list":"/paper/davit-dual-attention-vision-transformers#ran","syntology_url":"https://syntology.ai/paper/2204.03645","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.03645"}}}},{"rank_in_archive_order":83,"model":"BoTNet 200 (Mask R-CNN, single scale, 72 epochs)","metrics":{"AP50":"71.3","AP75":"54.6","box AP":"49.7"},"uses_additional_data":false,"paper_date":"2021-01-27","paper":"/paper/bottleneck-transformers-for-visual","paper_url":"https://arxiv.org/abs/2101.11605v2","paper_title":"Bottleneck Transformers for Visual Recognition","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":13,"official":null,"syntology":{"n_ran":26,"n_constructed":9,"n_ran_checked":19,"n_instrument":7,"n_unverified":23,"n_samples":49,"n_pointer_only_licence":8,"sample_list":"/paper/bottleneck-transformers-for-visual#ran","syntology_url":"https://syntology.ai/paper/2101.11605","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2101.11605"}}}},{"rank_in_archive_order":84,"model":"BoTNet 152 (Mask R-CNN, single scale, 72 epochs)","metrics":{"AP50":"71","AP75":"54.2","box AP":"49.5"},"uses_additional_data":false,"paper_date":"2021-01-27","paper":"/paper/bottleneck-transformers-for-visual","paper_url":"https://arxiv.org/abs/2101.11605v2","paper_title":"Bottleneck Transformers for Visual Recognition","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":13,"official":null,"syntology":{"n_ran":26,"n_constructed":9,"n_ran_checked":19,"n_instrument":7,"n_unverified":23,"n_samples":49,"n_pointer_only_licence":8,"sample_list":"/paper/bottleneck-transformers-for-visual#ran","syntology_url":"https://syntology.ai/paper/2101.11605","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2101.11605"}}}},{"rank_in_archive_order":85,"model":"DN-Deformable-DETR-R50++","metrics":{"AP50":"67.6","AP75":"53.8","APL":"65.4","APM":"52.6","APS":"31.3","Params (M)":"47","box AP":"49.5"},"uses_additional_data":false,"paper_date":"2022-03-02","paper":"/paper/dn-detr-accelerate-detr-training-by","paper_url":"https://arxiv.org/abs/2203.01305v3","paper_title":"DN-DETR: Accelerate DETR Training by Introducing Query DeNoising","code":"https://github.com/IDEACVR/DINO","n_code_links":17,"official":{"repos":["IDEA-Research/detrex","fengli-ust/dn-detr","idea-research/dn-detr"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":17,"n_constructed":3,"n_ran_checked":6,"n_instrument":11,"n_unverified":5,"n_samples":22,"n_pointer_only_licence":9,"sample_list":"/paper/dn-detr-accelerate-detr-training-by#ran","syntology_url":"https://syntology.ai/paper/2203.01305","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.01305"}}}},{"rank_in_archive_order":86,"model":"REGO-Deformable DETR-X101","metrics":{"AP50":"67.5","AP75":"53.1","APL":"65","APM":"52.6","APS":"30","box AP":"49.1"},"uses_additional_data":false,"paper_date":"2021-12-09","paper":"/paper/recurrent-glimpse-based-decoder-for-detection","paper_url":"https://arxiv.org/abs/2112.04632v2","paper_title":"Recurrent Glimpse-based Decoder for Detection with Transformer","code":"https://github.com/zhechen/deformable-detr-rego","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":87,"model":"CenterMask+VoVNet99 (multi-scale)","metrics":{"AP50":"67.8","box AP":"48.6"},"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":88,"model":"Mask R-CNN (ResNeXt-152-FPN, cascade)","metrics":{"AP50":"66.8","AP75":"52.9","box AP":"48.6"},"uses_additional_data":false,"paper_date":"2018-11-21","paper":"/paper/rethinking-imagenet-pre-training","paper_url":"http://arxiv.org/abs/1811.08883v1","paper_title":"Rethinking ImageNet Pre-training","code":"https://github.com/tensorpack/tensorpack/tree/master/examples/FasterRCNN","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":89,"model":"UniverseNet-20.08 (Res2Net-50, DCN, single-scale)","metrics":{"AP50":"67.0","AP75":"52.6","APL":"62.7","APM":"52.7","APS":"30.6","box AP":"48.5"},"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":90,"model":"XCiT-M24/8","metrics":{"box AP":"48.5"},"uses_additional_data":false,"paper_date":"2021-06-17","paper":"/paper/xcit-cross-covariance-image-transformers","paper_url":"https://arxiv.org/abs/2106.09681v2","paper_title":"XCiT: Cross-Covariance Image Transformers","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":12,"official":{"repos":["facebookresearch/xcit","rwightman/pytorch-image-models"],"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":["listed","official"]},"syntology":{"n_ran":10,"n_constructed":0,"n_ran_checked":8,"n_instrument":2,"n_unverified":4,"n_samples":14,"n_pointer_only_licence":11,"sample_list":"/paper/xcit-cross-covariance-image-transformers#ran","syntology_url":"https://syntology.ai/paper/2106.09681","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.09681"}}}},{"rank_in_archive_order":91,"model":"ELSA-S (Mask RCNN)","metrics":{"AP50":"70.4","AP75":"52.9","box AP":"48.3"},"uses_additional_data":false,"paper_date":"2021-12-23","paper":"/paper/elsa-enhanced-local-self-attention-for-vision","paper_url":"https://arxiv.org/abs/2112.12786v1","paper_title":"ELSA: Enhanced Local Self-Attention for Vision Transformer","code":"https://github.com/damo-cv/elsa","n_code_links":1,"official":{"repos":["damo-cv/elsa"],"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":0,"sample_list":"/paper/elsa-enhanced-local-self-attention-for-vision#ran","syntology_url":"https://syntology.ai/paper/2112.12786","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.12786"}}}},{"rank_in_archive_order":92,"model":"XCiT-S24/8","metrics":{"box AP":"48.1"},"uses_additional_data":false,"paper_date":"2021-06-17","paper":"/paper/xcit-cross-covariance-image-transformers","paper_url":"https://arxiv.org/abs/2106.09681v2","paper_title":"XCiT: Cross-Covariance Image Transformers","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":12,"official":{"repos":["facebookresearch/xcit","rwightman/pytorch-image-models"],"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":["listed","official"]},"syntology":{"n_ran":10,"n_constructed":0,"n_ran_checked":8,"n_instrument":2,"n_unverified":4,"n_samples":14,"n_pointer_only_licence":11,"sample_list":"/paper/xcit-cross-covariance-image-transformers#ran","syntology_url":"https://syntology.ai/paper/2106.09681","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.09681"}}}},{"rank_in_archive_order":93,"model":"GCNet (ResNeXt-101 + DCN + cascade + GC r16)","metrics":{"AP50":"66.9","AP75":"52.2","box AP":"47.9"},"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":94,"model":"MAE-Det(MAE-Det-L+GFLV2)","metrics":{"AP50":"65.5","AP75":"52.2","APL":"61.1","APM":"51.9","APS":"30.3","box AP":"47.8"},"uses_additional_data":false,"paper_date":"2021-11-26","paper":"/paper/revisiting-efficient-object-detection","paper_url":"https://arxiv.org/abs/2111.13336v5","paper_title":"MAE-DET: Revisiting Maximum Entropy Principle in Zero-Shot NAS for Efficient Object Detection","code":"https://github.com/alibaba/lightweight-neural-architecture-search","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":95,"model":"Res2Net101+HTC","metrics":{"AP50":"66.5","AP75":"51.3","APL":"62.1","APM":"51.6","APS":"28.6","box AP":"47.5"},"uses_additional_data":false,"paper_date":"2019-04-02","paper":"/paper/res2net-a-new-multi-scale-backbone","paper_url":"https://arxiv.org/abs/1904.01169v3","paper_title":"Res2Net: A New Multi-scale Backbone Architecture","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":34,"official":null,"syntology":{"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":4,"n_samples":9,"n_pointer_only_licence":9,"sample_list":"/paper/res2net-a-new-multi-scale-backbone#ran","syntology_url":"https://syntology.ai/paper/1904.01169","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.01169"}}}},{"rank_in_archive_order":96,"model":"Mask R-CNN (ResNet-101-FPN, GN, Cascade)","metrics":{"box AP":"47.4"},"uses_additional_data":false,"paper_date":"2018-11-21","paper":"/paper/rethinking-imagenet-pre-training","paper_url":"http://arxiv.org/abs/1811.08883v1","paper_title":"Rethinking ImageNet Pre-training","code":"https://github.com/tensorpack/tensorpack/tree/master/examples/FasterRCNN","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":97,"model":"Pix2seq (R50-C4)","metrics":{"box AP":"47.3"},"uses_additional_data":false,"paper_date":"2021-09-22","paper":"/paper/pix2seq-a-language-modeling-framework-for","paper_url":"https://arxiv.org/abs/2109.10852v2","paper_title":"Pix2seq: A Language Modeling Framework for Object Detection","code":"https://github.com/google-research/pix2seq","n_code_links":6,"official":{"repos":["google-research/pix2seq"],"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":3,"n_ran_checked":6,"n_instrument":4,"n_unverified":2,"n_samples":12,"n_pointer_only_licence":10,"sample_list":"/paper/pix2seq-a-language-modeling-framework-for#ran","syntology_url":"https://syntology.ai/paper/2109.10852","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.10852"}}}},{"rank_in_archive_order":98,"model":"Pix2seq (ViT-B)","metrics":{"box AP":"47.1"},"uses_additional_data":false,"paper_date":"2021-09-22","paper":"/paper/pix2seq-a-language-modeling-framework-for","paper_url":"https://arxiv.org/abs/2109.10852v2","paper_title":"Pix2seq: A Language Modeling Framework for Object Detection","code":"https://github.com/google-research/pix2seq","n_code_links":6,"official":{"repos":["google-research/pix2seq"],"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":3,"n_ran_checked":6,"n_instrument":4,"n_unverified":2,"n_samples":12,"n_pointer_only_licence":10,"sample_list":"/paper/pix2seq-a-language-modeling-framework-for#ran","syntology_url":"https://syntology.ai/paper/2109.10852","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.10852"}}}},{"rank_in_archive_order":99,"model":"HTC (HRNetV2p-W48)","metrics":{"APL":"62.2","APM":"50.3","APS":"28.8","box AP":"47.0"},"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":100,"model":"PatchConvNet-S120 (Mask R-CNN)","metrics":{"box AP":"47.0"},"uses_additional_data":false,"paper_date":"2021-12-27","paper":"/paper/augmenting-convolutional-networks-with","paper_url":"https://arxiv.org/abs/2112.13692v1","paper_title":"Augmenting Convolutional networks with attention-based aggregation","code":"https://github.com/facebookresearch/deit","n_code_links":5,"official":{"repos":["facebookresearch/deit"],"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":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/augmenting-convolutional-networks-with#ran","syntology_url":"https://syntology.ai/paper/2112.13692","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.13692"}}}},{"rank_in_archive_order":101,"model":"RPDet (ResNeXt-101-DCN, multi-scale)","metrics":{"box AP":"46.8"},"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":102,"model":"DAB-DETR-DC5-R101","metrics":{"AP50":"67","AP75":"50.2","APL":"64.1","APM":"50.5","APS":"28.1","Params (M)":"63","box AP":"46.6"},"uses_additional_data":false,"paper_date":"2022-01-28","paper":"/paper/dab-detr-dynamic-anchor-boxes-are-better-1","paper_url":"https://arxiv.org/abs/2201.12329v4","paper_title":"DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR","code":"https://github.com/IDEA-Research/detrex","n_code_links":8,"official":{"repos":["slongliu/dab-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":6,"n_constructed":3,"n_ran_checked":4,"n_instrument":2,"n_unverified":5,"n_samples":11,"n_pointer_only_licence":0,"sample_list":"/paper/dab-detr-dynamic-anchor-boxes-are-better-1#ran","syntology_url":"https://syntology.ai/paper/2201.12329","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.12329"}}}},{"rank_in_archive_order":103,"model":"DyHead (ResNet-101)","metrics":{"box AP":"46.5"},"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":104,"model":"Mask R-CNN (ResNeXt-152-FPN)","metrics":{"AP50":"67.1","AP75":"51.1","box AP":"46.4"},"uses_additional_data":false,"paper_date":"2018-11-21","paper":"/paper/rethinking-imagenet-pre-training","paper_url":"http://arxiv.org/abs/1811.08883v1","paper_title":"Rethinking ImageNet Pre-training","code":"https://github.com/tensorpack/tensorpack/tree/master/examples/FasterRCNN","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":105,"model":"RPDet (ResNet-101-DCN, multi-scale)","metrics":{"box AP":"46.4"},"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":106,"model":"PatchConvNet-S60 (Mask R-CNN)","metrics":{"box AP":"46.4"},"uses_additional_data":false,"paper_date":"2021-12-27","paper":"/paper/augmenting-convolutional-networks-with","paper_url":"https://arxiv.org/abs/2112.13692v1","paper_title":"Augmenting Convolutional networks with attention-based aggregation","code":"https://github.com/facebookresearch/deit","n_code_links":5,"official":{"repos":["facebookresearch/deit"],"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":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/augmenting-convolutional-networks-with#ran","syntology_url":"https://syntology.ai/paper/2112.13692","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.13692"}}}},{"rank_in_archive_order":107,"model":"Cascade Mask R-CNN (ResNet-50)","metrics":{"AP50":"64.3","AP75":"50.5","box AP":"46.3"},"uses_additional_data":false,"paper_date":"2015-12-10","paper":"/paper/deep-residual-learning-for-image-recognition","paper_url":"http://arxiv.org/abs/1512.03385v1","paper_title":"Deep Residual Learning for Image Recognition","code":"https://github.com/tensorflow/models/tree/master/research/deeplab","n_code_links":484,"official":{"repos":["KaimingHe/resnet-1k-layers"],"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":254,"n_constructed":108,"n_ran_checked":163,"n_instrument":91,"n_unverified":123,"n_samples":377,"n_pointer_only_licence":193,"sample_list":"/paper/deep-residual-learning-for-image-recognition#ran","syntology_url":"https://syntology.ai/paper/1512.03385","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1512.03385"}}}},{"rank_in_archive_order":108,"model":"HoughNet (HG-104, MS)","metrics":{"AP50":"64.6","AP75":"50.3","APL":"59.7","APM":"48.8","APS":"30.0","box AP":"46.1"},"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":109,"model":"Mask R-CNN (HRNetV2p-W48, cascade)","metrics":{"APL":"60.1","APS":"27.5","box AP":"46.0"},"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":110,"model":"Conditional DETR-DC5-R101","metrics":{"AP50":"66.8","AP75":"49.5","APL":"63.3","APM":"50.3","APS":"27.2","Params (M)":"63","box AP":"45.9"},"uses_additional_data":false,"paper_date":"2021-08-13","paper":"/paper/conditional-detr-for-fast-training","paper_url":"https://arxiv.org/abs/2108.06152v3","paper_title":"Conditional DETR for Fast Training Convergence","code":"https://github.com/huggingface/transformers","n_code_links":4,"official":{"repos":["atten4vis/conditionaldetr"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":6,"n_constructed":1,"n_ran_checked":3,"n_instrument":3,"n_unverified":3,"n_samples":9,"n_pointer_only_licence":4,"sample_list":"/paper/conditional-detr-for-fast-training#ran","syntology_url":"https://syntology.ai/paper/2108.06152","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.06152"}}}},{"rank_in_archive_order":111,"model":"BoTNet 50 (72 epochs)","metrics":{"box AP":"45.9"},"uses_additional_data":false,"paper_date":"2021-01-27","paper":"/paper/bottleneck-transformers-for-visual","paper_url":"https://arxiv.org/abs/2101.11605v2","paper_title":"Bottleneck Transformers for Visual Recognition","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":13,"official":null,"syntology":{"n_ran":26,"n_constructed":9,"n_ran_checked":19,"n_instrument":7,"n_unverified":23,"n_samples":49,"n_pointer_only_licence":8,"sample_list":"/paper/bottleneck-transformers-for-visual#ran","syntology_url":"https://syntology.ai/paper/2101.11605","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2101.11605"}}}},{"rank_in_archive_order":112,"model":"Sparse R-CNN (ResNet-101, learnable proposals, random crop aug, FPN)","metrics":{"AP50":"64.6","AP75":"49.5","APL":"61.6","APM":"48.3","APS":"28.3","box AP":"45.6"},"uses_additional_data":false,"paper_date":"2020-11-25","paper":"/paper/sparse-r-cnn-end-to-end-object-detection-with","paper_url":"https://arxiv.org/abs/2011.12450v2","paper_title":"Sparse R-CNN: End-to-End Object Detection with Learnable Proposals","code":"https://github.com/open-mmlab/mmdetection","n_code_links":6,"official":null,"syntology":null},{"rank_in_archive_order":113,"model":"CenterMask+VoVNetV2-99 (single-scale)","metrics":{"APL":"58.8","APS":"29.2","box AP":"45.6"},"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":114,"model":"HTC (HRNetV2p-W32)","metrics":{"APL":"59.5","APM":"48.4","APS":"27.0","box AP":"45.3"},"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":115,"model":"Anchor DETR-DC5-R101","metrics":{"AP50":"65.7","AP75":"48.8","APL":"61.6","APM":"49.4","APS":"25.8","box AP":"45.1"},"uses_additional_data":false,"paper_date":"2021-09-15","paper":"/paper/anchor-detr-query-design-for-transformer","paper_url":"https://arxiv.org/abs/2109.07107v2","paper_title":"Anchor DETR: Query Design for Transformer-Based Object Detection","code":"https://github.com/megvii-research/AnchorDETR","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":116,"model":"Conditional DETR-DC5-R50","metrics":{"AP50":"65.4","AP75":"48.5","APL":"62.2","APM":"49","APS":"25.3","Params (M)":"44","box AP":"45.1"},"uses_additional_data":false,"paper_date":"2021-08-13","paper":"/paper/conditional-detr-for-fast-training","paper_url":"https://arxiv.org/abs/2108.06152v3","paper_title":"Conditional DETR for Fast Training Convergence","code":"https://github.com/huggingface/transformers","n_code_links":4,"official":{"repos":["atten4vis/conditionaldetr"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":6,"n_constructed":1,"n_ran_checked":3,"n_instrument":3,"n_unverified":3,"n_samples":9,"n_pointer_only_licence":4,"sample_list":"/paper/conditional-detr-for-fast-training#ran","syntology_url":"https://syntology.ai/paper/2108.06152","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.06152"}}}},{"rank_in_archive_order":117,"model":"Mask R-CNN (ResNeXt-152 + 1 NL)","metrics":{"AP50":"67.8","AP75":"48.9","box AP":"45.0"},"uses_additional_data":false,"paper_date":"2017-11-21","paper":"/paper/non-local-neural-networks","paper_url":"http://arxiv.org/abs/1711.07971v3","paper_title":"Non-local Neural Networks","code":"https://github.com/facebookresearch/detectron","n_code_links":32,"official":{"repos":["facebookresearch/video-nonlocal-net"],"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":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":1,"n_samples":4,"n_pointer_only_licence":4,"sample_list":"/paper/non-local-neural-networks#ran","syntology_url":"https://syntology.ai/paper/1711.07971","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1711.07971"}}}},{"rank_in_archive_order":118,"model":"Pix2seq (R101-DC5)","metrics":{"AP50":"63.2","AP75":"48.6","APL":"60.4","APM":"48.9","APS":"28.2","box AP":"45.0"},"uses_additional_data":false,"paper_date":"2021-09-22","paper":"/paper/pix2seq-a-language-modeling-framework-for","paper_url":"https://arxiv.org/abs/2109.10852v2","paper_title":"Pix2seq: A Language Modeling Framework for Object Detection","code":"https://github.com/google-research/pix2seq","n_code_links":6,"official":{"repos":["google-research/pix2seq"],"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":3,"n_ran_checked":6,"n_instrument":4,"n_unverified":2,"n_samples":12,"n_pointer_only_licence":10,"sample_list":"/paper/pix2seq-a-language-modeling-framework-for#ran","syntology_url":"https://syntology.ai/paper/2109.10852","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.10852"}}}},{"rank_in_archive_order":119,"model":"Mask R-CNN-FPN (AOGNet-40M)","metrics":{"AP50":"66.2","AP75":"49.1","box AP":"44.9"},"uses_additional_data":false,"paper_date":"2019-08-04","paper":"/paper/attentive-normalization","paper_url":"https://arxiv.org/abs/1908.01259v3","paper_title":"Attentive Normalization","code":"https://github.com/iVMCL/AOGNet-v2","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":120,"model":"DETR-DC5 (ResNet-101)","metrics":{"AP50":"64.7","AP75":"47.7","APL":"62.3","APM":"49.5","APS":"23.7","box AP":"44.9"},"uses_additional_data":false,"paper_date":"2020-05-26","paper":"/paper/end-to-end-object-detection-with-transformers","paper_url":"https://arxiv.org/abs/2005.12872v3","paper_title":"End-to-End Object Detection with Transformers","code":"https://github.com/huggingface/transformers","n_code_links":37,"official":{"repos":["facebookresearch/detr"],"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":["listed","official"]},"syntology":{"n_ran":70,"n_constructed":45,"n_ran_checked":62,"n_instrument":8,"n_unverified":22,"n_samples":92,"n_pointer_only_licence":19,"sample_list":"/paper/end-to-end-object-detection-with-transformers#ran","syntology_url":"https://syntology.ai/paper/2005.12872","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.12872"}}}},{"rank_in_archive_order":121,"model":"Mask R-CNN (VoVNetV2-99, single-scale)","metrics":{"APL":"57.7","APS":"28.5","box AP":"44.9"},"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":122,"model":"R3-CNN (ResNet-50-FPN, DCN)","metrics":{"AP50":"64.3","AP75":"48.9","APL":"59.6","APM":"48.3","APS":"26.6","box AP":"44.8"},"uses_additional_data":false,"paper_date":"2021-04-03","paper":"/paper/recursively-refined-r-cnn-instance","paper_url":"https://arxiv.org/abs/2104.01329v2","paper_title":"Recursively Refined R-CNN: Instance Segmentation with Self-RoI Rebalancing","code":"https://github.com/IMPLabUniPr/mmdetection","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":123,"model":"RPDet (ResNet-101-DCN, multi-scale train)","metrics":{"box AP":"44.8"},"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":124,"model":"RetinaNet (ViL-Base, multi-scale, 3x)","metrics":{"AP75":"47.6","APL":"58.1","APM":"48","APS":"29.9","box AP":"44.7"},"uses_additional_data":false,"paper_date":"2021-03-29","paper":"/paper/2103-15358","paper_url":"https://arxiv.org/abs/2103.15358v2","paper_title":"Multi-Scale Vision Longformer: A New Vision Transformer for High-Resolution Image Encoding","code":"https://github.com/microsoft/esvit","n_code_links":3,"official":{"repos":["microsoft/vision-longformer"],"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":0,"n_ran_checked":5,"n_instrument":3,"n_unverified":2,"n_samples":10,"n_pointer_only_licence":2,"sample_list":"/paper/2103-15358#ran","syntology_url":"https://syntology.ai/paper/2103.15358","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.15358"}}}},{"rank_in_archive_order":125,"model":"Cascade R-CNN (HRNetV2p-W48)","metrics":{"AP50":"62.7","AP75":"48.7","APL":"58.5","APM":"48.1","APS":"26.3","box AP":"44.6"},"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":126,"model":"CenterMask+VoVNetV2-57 (single-scale)","metrics":{"APM":"48.3","APS":"27.7","box AP":"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":127,"model":"Conditional DETR-R101","metrics":{"AP50":"65.6","AP75":"47.5","APL":"63.6","APM":"48.4","APS":"23.6","Params (M)":"63","box AP":"44.5"},"uses_additional_data":false,"paper_date":"2021-08-13","paper":"/paper/conditional-detr-for-fast-training","paper_url":"https://arxiv.org/abs/2108.06152v3","paper_title":"Conditional DETR for Fast Training Convergence","code":"https://github.com/huggingface/transformers","n_code_links":4,"official":{"repos":["atten4vis/conditionaldetr"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":6,"n_constructed":1,"n_ran_checked":3,"n_instrument":3,"n_unverified":3,"n_samples":9,"n_pointer_only_licence":4,"sample_list":"/paper/conditional-detr-for-fast-training#ran","syntology_url":"https://syntology.ai/paper/2108.06152","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.06152"}}}},{"rank_in_archive_order":128,"model":"Sparse R-CNN (ResNet-50, learnable proposals, random crop aug, FPN)","metrics":{"AP50":"63.4","AP75":"48.2","APL":"59.5","APM":"47.2","APS":"26.9","box AP":"44.5"},"uses_additional_data":false,"paper_date":"2020-11-25","paper":"/paper/sparse-r-cnn-end-to-end-object-detection-with","paper_url":"https://arxiv.org/abs/2011.12450v2","paper_title":"Sparse R-CNN: End-to-End Object Detection with Learnable Proposals","code":"https://github.com/open-mmlab/mmdetection","n_code_links":6,"official":null,"syntology":null},{"rank_in_archive_order":129,"model":"GFL (ResNet-50)","metrics":{"AP50":"63.0","AP75":"48.3","box AP":"44.5"},"uses_additional_data":false,"paper_date":"2015-12-10","paper":"/paper/deep-residual-learning-for-image-recognition","paper_url":"http://arxiv.org/abs/1512.03385v1","paper_title":"Deep Residual Learning for Image Recognition","code":"https://github.com/tensorflow/models/tree/master/research/deeplab","n_code_links":484,"official":{"repos":["KaimingHe/resnet-1k-layers"],"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":254,"n_constructed":108,"n_ran_checked":163,"n_instrument":91,"n_unverified":123,"n_samples":377,"n_pointer_only_licence":193,"sample_list":"/paper/deep-residual-learning-for-image-recognition#ran","syntology_url":"https://syntology.ai/paper/1512.03385","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1512.03385"}}}},{"rank_in_archive_order":130,"model":"RPDet (ResNeXt-101-DCN)","metrics":{"box AP":"44.5"},"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":131,"model":"CenterMask+X101-32x8d (single-scale)","metrics":{"APL":"57.1","APS":"26.7","box AP":"44.4"},"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":132,"model":"RetinaNet (ViL-Base)","metrics":{"AP50":"65.5","AP75":"47.1","APL":"58.3","APM":"47.9","APS":"28.9","box AP":"44.3"},"uses_additional_data":false,"paper_date":"2021-03-29","paper":"/paper/2103-15358","paper_url":"https://arxiv.org/abs/2103.15358v2","paper_title":"Multi-Scale Vision Longformer: A New Vision Transformer for High-Resolution Image Encoding","code":"https://github.com/microsoft/esvit","n_code_links":3,"official":{"repos":["microsoft/vision-longformer"],"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":0,"n_ran_checked":5,"n_instrument":3,"n_unverified":2,"n_samples":10,"n_pointer_only_licence":2,"sample_list":"/paper/2103-15358#ran","syntology_url":"https://syntology.ai/paper/2103.15358","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.15358"}}}},{"rank_in_archive_order":133,"model":"R3-CNN (ResNet-50-FPN, GC-Net)","metrics":{"AP50":"64.1","AP75":"48.4","APL":"58.9","APM":"47.1","APS":"27","box AP":"44.3"},"uses_additional_data":false,"paper_date":"2021-04-03","paper":"/paper/recursively-refined-r-cnn-instance","paper_url":"https://arxiv.org/abs/2104.01329v2","paper_title":"Recursively Refined R-CNN: Instance Segmentation with Self-RoI Rebalancing","code":"https://github.com/IMPLabUniPr/mmdetection","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":134,"model":"Anchor DETR-DC5-R50","metrics":{"AP50":"64.7","AP75":"47.5","APL":"60.6","APM":"48.2","APS":"24.7","box AP":"44.2"},"uses_additional_data":false,"paper_date":"2021-09-15","paper":"/paper/anchor-detr-query-design-for-transformer","paper_url":"https://arxiv.org/abs/2109.07107v2","paper_title":"Anchor DETR: Query Design for Transformer-Based Object Detection","code":"https://github.com/megvii-research/AnchorDETR","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":135,"model":"DAB-DETR-R101","metrics":{"AP50":"64.7","AP75":"47.2","APL":"62.9","APM":"48.2","APS":"24.1","Params (M)":"63","box AP":"44.1"},"uses_additional_data":false,"paper_date":"2022-01-28","paper":"/paper/dab-detr-dynamic-anchor-boxes-are-better-1","paper_url":"https://arxiv.org/abs/2201.12329v4","paper_title":"DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR","code":"https://github.com/IDEA-Research/detrex","n_code_links":8,"official":{"repos":["slongliu/dab-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":6,"n_constructed":3,"n_ran_checked":4,"n_instrument":2,"n_unverified":5,"n_samples":11,"n_pointer_only_licence":0,"sample_list":"/paper/dab-detr-dynamic-anchor-boxes-are-better-1#ran","syntology_url":"https://syntology.ai/paper/2201.12329","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.12329"}}}},{"rank_in_archive_order":136,"model":"Faster RCNN-R101-FPN+","metrics":{"AP50":"63.9","AP75":"47.8","APL":"56","APM":"48.1","APS":"27.2","box AP":"44"},"uses_additional_data":false,"paper_date":"2020-05-26","paper":"/paper/end-to-end-object-detection-with-transformers","paper_url":"https://arxiv.org/abs/2005.12872v3","paper_title":"End-to-End Object Detection with Transformers","code":"https://github.com/huggingface/transformers","n_code_links":37,"official":{"repos":["facebookresearch/detr"],"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":["listed","official"]},"syntology":{"n_ran":70,"n_constructed":45,"n_ran_checked":62,"n_instrument":8,"n_unverified":22,"n_samples":92,"n_pointer_only_licence":19,"sample_list":"/paper/end-to-end-object-detection-with-transformers#ran","syntology_url":"https://syntology.ai/paper/2005.12872","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.12872"}}}},{"rank_in_archive_order":137,"model":"Cascade R-CNN (HRNetV2p-W32)","metrics":{"AP50":"61.7","AP75":"47.7","APL":"57.4","APM":"46.5","APS":"25.6","box AP":"43.7"},"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":138,"model":"Sparse R-CNN (ResNet-101, FPN)","metrics":{"AP50":"62.1","AP75":"47.2","APL":"59.7","APM":"46.3","APS":"26.1","box AP":"43.5"},"uses_additional_data":false,"paper_date":"2020-11-25","paper":"/paper/sparse-r-cnn-end-to-end-object-detection-with","paper_url":"https://arxiv.org/abs/2011.12450v2","paper_title":"Sparse R-CNN: End-to-End Object Detection with Learnable Proposals","code":"https://github.com/open-mmlab/mmdetection","n_code_links":6,"official":null,"syntology":null},{"rank_in_archive_order":139,"model":"ATSS (ResNet-50)","metrics":{"AP50":"61.9","AP75":"47.0","box AP":"43.5"},"uses_additional_data":false,"paper_date":"2015-12-10","paper":"/paper/deep-residual-learning-for-image-recognition","paper_url":"http://arxiv.org/abs/1512.03385v1","paper_title":"Deep Residual Learning for Image Recognition","code":"https://github.com/tensorflow/models/tree/master/research/deeplab","n_code_links":484,"official":{"repos":["KaimingHe/resnet-1k-layers"],"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":254,"n_constructed":108,"n_ran_checked":163,"n_instrument":91,"n_unverified":123,"n_samples":377,"n_pointer_only_licence":193,"sample_list":"/paper/deep-residual-learning-for-image-recognition#ran","syntology_url":"https://syntology.ai/paper/1512.03385","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1512.03385"}}}},{"rank_in_archive_order":140,"model":"PVT-Large (RetinaNet 3x,MS)","metrics":{"AP50":"63.6","AP75":"46.1","APL":"59.5","APM":"46.0","APS":"26.1","box AP":"43.4"},"uses_additional_data":false,"paper_date":"2021-02-24","paper":"/paper/pyramid-vision-transformer-a-versatile","paper_url":"https://arxiv.org/abs/2102.12122v2","paper_title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","code":"https://github.com/open-mmlab/mmdetection","n_code_links":11,"official":{"repos":["whai362/PVT"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":4,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":22,"n_constructed":16,"n_ran_checked":18,"n_instrument":4,"n_unverified":8,"n_samples":30,"n_pointer_only_licence":1,"sample_list":"/paper/pyramid-vision-transformer-a-versatile#ran","syntology_url":"https://syntology.ai/paper/2102.12122","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.12122"}}}},{"rank_in_archive_order":141,"model":"ExtremeNet (Hourglass-104, multi-scale)","metrics":{"AP50":"59.6","AP75":"46.8","APL":"59.4","APM":"46.6","APS":"25.7","box AP":"43.3"},"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":142,"model":"Pix2seq (R50-DC5 )","metrics":{"AP50":"61.0","AP75":"46.1","APL":"58.6","APM":"47","APS":"26.6","box AP":"43.2"},"uses_additional_data":false,"paper_date":"2021-09-22","paper":"/paper/pix2seq-a-language-modeling-framework-for","paper_url":"https://arxiv.org/abs/2109.10852v2","paper_title":"Pix2seq: A Language Modeling Framework for Object Detection","code":"https://github.com/google-research/pix2seq","n_code_links":6,"official":{"repos":["google-research/pix2seq"],"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":3,"n_ran_checked":6,"n_instrument":4,"n_unverified":2,"n_samples":12,"n_pointer_only_licence":10,"sample_list":"/paper/pix2seq-a-language-modeling-framework-for#ran","syntology_url":"https://syntology.ai/paper/2109.10852","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.10852"}}}},{"rank_in_archive_order":143,"model":"HTC (cascade)","metrics":{"AP50":"59.4","AP75":"40.7","APL":"52.3","APM":"40.9","APS":"20.3","box AP":"43.2"},"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":144,"model":"Mask R-CNN-FPN (ResNeXt-101, GN+WS)","metrics":{"AP50":"64.15","AP75":"47.11","APL":"56.39","APM":"47.19","APS":"25.49","box AP":"43.12"},"uses_additional_data":false,"paper_date":"2019-03-25","paper":"/paper/weight-standardization","paper_url":"https://arxiv.org/abs/1903.10520v2","paper_title":"Micro-Batch Training with Batch-Channel Normalization and Weight Standardization","code":"https://github.com/labmlai/annotated_deep_learning_paper_implementations","n_code_links":7,"official":null,"syntology":null},{"rank_in_archive_order":145,"model":"HTC (HRNetV2p-W18)","metrics":{"APM":"46.0","APS":"26.6","box AP":"43.1"},"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":146,"model":"Mask R-CNN (ResNet-101, DCNv2)","metrics":{"box AP":"43.1"},"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":147,"model":"Conditional DETR-R50","metrics":{"AP50":"64","AP75":"45.7","APL":"61.5","APM":"46.7","APS":"22.7","Params (M)":"44","box AP":"43"},"uses_additional_data":false,"paper_date":"2021-08-13","paper":"/paper/conditional-detr-for-fast-training","paper_url":"https://arxiv.org/abs/2108.06152v3","paper_title":"Conditional DETR for Fast Training Convergence","code":"https://github.com/huggingface/transformers","n_code_links":4,"official":{"repos":["atten4vis/conditionaldetr"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":6,"n_constructed":1,"n_ran_checked":3,"n_instrument":3,"n_unverified":3,"n_samples":9,"n_pointer_only_licence":4,"sample_list":"/paper/conditional-detr-for-fast-training#ran","syntology_url":"https://syntology.ai/paper/2108.06152","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.06152"}}}},{"rank_in_archive_order":148,"model":"HoughNet (HG-104)","metrics":{"AP50":"62.2","AP75":"46.9","APL":"55.8","APM":"47.6","APS":"25.5","box AP":"43.0"},"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":149,"model":"Faster R-CNN (FPN, X-volution)","metrics":{"AP50":"64","AP75":"46.4","APL":"55","APM":"46","APS":"26.9","box AP":"42.8"},"uses_additional_data":false,"paper_date":"2021-06-04","paper":"/paper/x-volution-on-the-unification-of-convolution","paper_url":"https://arxiv.org/abs/2106.02253v2","paper_title":"X-volution: On the unification of convolution and self-attention","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":150,"model":"Cascade R-CNN (ResNet-101-FPN+, cascade)","metrics":{"AP50":"61.6","AP75":"46.6","APL":"57.4","APM":"46.2","APS":"23.8","box AP":"42.7"},"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":151,"model":"PVT-Large (RetinaNet 1x)","metrics":{"AP50":"63.7","AP75":"45.4","APL":"58.4","APM":"46.0","APS":"25.8","box AP":"42.6"},"uses_additional_data":false,"paper_date":"2021-02-24","paper":"/paper/pyramid-vision-transformer-a-versatile","paper_url":"https://arxiv.org/abs/2102.12122v2","paper_title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","code":"https://github.com/open-mmlab/mmdetection","n_code_links":11,"official":{"repos":["whai362/PVT"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":4,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":22,"n_constructed":16,"n_ran_checked":18,"n_instrument":4,"n_unverified":8,"n_samples":30,"n_pointer_only_licence":1,"sample_list":"/paper/pyramid-vision-transformer-a-versatile#ran","syntology_url":"https://syntology.ai/paper/2102.12122","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.12122"}}}},{"rank_in_archive_order":152,"model":"CornerNet-Saccade (Hourglass-54)","metrics":{"APL":"58.4","APM":"44.3","APS":"25.5","box AP":"42.6"},"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":153,"model":"Pix2seq (R50)","metrics":{"box AP":"42.6"},"uses_additional_data":false,"paper_date":"2021-09-22","paper":"/paper/pix2seq-a-language-modeling-framework-for","paper_url":"https://arxiv.org/abs/2109.10852v2","paper_title":"Pix2seq: A Language Modeling Framework for Object Detection","code":"https://github.com/google-research/pix2seq","n_code_links":6,"official":{"repos":["google-research/pix2seq"],"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":3,"n_ran_checked":6,"n_instrument":4,"n_unverified":2,"n_samples":12,"n_pointer_only_licence":10,"sample_list":"/paper/pix2seq-a-language-modeling-framework-for#ran","syntology_url":"https://syntology.ai/paper/2109.10852","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.10852"}}}},{"rank_in_archive_order":154,"model":"Mask R-CNN (ResNet-101-FPN, GroupNorm, long)","metrics":{"AP50":"62.8","AP75":"46.2","box AP":"42.3"},"uses_additional_data":false,"paper_date":"2018-03-22","paper":"/paper/group-normalization","paper_url":"http://arxiv.org/abs/1803.08494v3","paper_title":"Group Normalization","code":"https://github.com/labmlai/annotated_deep_learning_paper_implementations","n_code_links":22,"official":{"repos":["ppwwyyxx/GroupNorm-reproduce"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":7,"n_constructed":2,"n_ran_checked":5,"n_instrument":2,"n_unverified":8,"n_samples":15,"n_pointer_only_licence":5,"sample_list":"/paper/group-normalization#ran","syntology_url":"https://syntology.ai/paper/1803.08494","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1803.08494"}}}},{"rank_in_archive_order":155,"model":"Sparse R-CNN (ResNet-50, FPN)","metrics":{"AP50":"61.2","AP75":"45.7","APL":"57.6","APM":"44.6","APS":"26.7","box AP":"42.3"},"uses_additional_data":false,"paper_date":"2020-11-25","paper":"/paper/sparse-r-cnn-end-to-end-object-detection-with","paper_url":"https://arxiv.org/abs/2011.12450v2","paper_title":"Sparse R-CNN: End-to-End Object Detection with Learnable Proposals","code":"https://github.com/open-mmlab/mmdetection","n_code_links":6,"official":null,"syntology":null},{"rank_in_archive_order":156,"model":"Mask R-CNN (HRNetV2p-W32)","metrics":{"APM":"45.4","APS":"25.0","box AP":"42.3"},"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":157,"model":"DETR-ResNet50 with iRPE-K (300 epochs)","metrics":{"box AP":"42.3"},"uses_additional_data":false,"paper_date":"2021-07-29","paper":"/paper/rethinking-and-improving-relative-position","paper_url":"https://arxiv.org/abs/2107.14222v1","paper_title":"Rethinking and Improving Relative Position Encoding for Vision Transformer","code":"https://github.com/microsoft/cream","n_code_links":1,"official":{"repos":["microsoft/cream"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]},"syntology":{"n_ran":7,"n_constructed":0,"n_ran_checked":0,"n_instrument":7,"n_unverified":2,"n_samples":9,"n_pointer_only_licence":0,"sample_list":"/paper/rethinking-and-improving-relative-position#ran","syntology_url":"https://syntology.ai/paper/2107.14222","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.14222"}}}},{"rank_in_archive_order":158,"model":"TridentNet (ResNet-101)","metrics":{"AP50":"63.5","AP75":"45.5","APL":"56.9","APM":"47","APS":"24.9","box AP":"42"},"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":159,"model":"R3-CNN (ResNet-50-FPN)","metrics":{"AP50":"61","AP75":"46.3","APL":"55.7","APM":"45.2","APS":"24.5","box AP":"42"},"uses_additional_data":false,"paper_date":"2021-04-03","paper":"/paper/recursively-refined-r-cnn-instance","paper_url":"https://arxiv.org/abs/2104.01329v2","paper_title":"Recursively Refined R-CNN: Instance Segmentation with Self-RoI Rebalancing","code":"https://github.com/IMPLabUniPr/mmdetection","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":160,"model":"Faster R-CNN (HRNetV2p-W48)","metrics":{"AP50":"62.8","AP75":"45.9","APL":"54.6","APM":"44.7","box AP":"41.8"},"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":161,"model":"Faster R-CNN (LIP-ResNet-101)","metrics":{"AP50":"63.6","AP75":"45.6","APM":"45.8","APS":"25.2","box AP":"41.7"},"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":162,"model":"Faster R-CNN (ResNet-101, DCNv2)","metrics":{"APL":"58.7","APM":"45.8","APS":"22.2","box AP":"41.7"},"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":163,"model":"FSAF (ResNeXt-101, anchor-based branches)","metrics":{"AP50":"62.4","box AP":"41.6"},"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":164,"model":"CornerNet-Saccade (Hourglass-104)","metrics":{"APL":"57.1","APM":"43.5","APS":"23.8","box AP":"41.4"},"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":165,"model":"Grid R-CNN (ResNet-101-FPN)","metrics":{"AP50":"60.3","AP75":"44.4","APL":"54.1","APM":"45.8","APS":"23.4","box AP":"41.3"},"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":166,"model":"Cascade R-CNN (HRNetV2p-W18)","metrics":{"AP50":"59.2","AP75":"44.9","APL":"54.1","APM":"44.2","APS":"23.7","box AP":"41.3"},"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":167,"model":"CenterNet511 (Hourglass-52)","metrics":{"AP50":"59.2","AP75":"43.9","APL":"55.8","APM":"43.8","APS":"23.6","box AP":"41.3"},"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":168,"model":"RetinaMask (ResNet-101-FPN)","metrics":{"AP50":"60.2","AP75":"44.1","box AP":"41.1"},"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":169,"model":"PoolFormer-S36 (Mask R-CNN)","metrics":{"AP50":"63.1","AP75":"44.8","box AP":"41.0"},"uses_additional_data":false,"paper_date":"2021-11-22","paper":"/paper/metaformer-is-actually-what-you-need-for","paper_url":"https://arxiv.org/abs/2111.11418v3","paper_title":"MetaFormer Is Actually What You Need for Vision","code":"https://github.com/huggingface/transformers","n_code_links":18,"official":{"repos":["rwightman/pytorch-image-models","sail-sg/poolformer"],"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":1,"sample_list":"/paper/metaformer-is-actually-what-you-need-for#ran","syntology_url":"https://syntology.ai/paper/2111.11418","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.11418"}}}},{"rank_in_archive_order":170,"model":"Faster R-CNN (HRNetV2p-W32)","metrics":{"AP50":"61.8","AP75":"44.8","APL":"53.3","APM":"43.7","APS":"24.4","box AP":"40.9"},"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":171,"model":"VirTex Mask R-CNN (ResNet-50-FPN)","metrics":{"box AP":"40.9"},"uses_additional_data":false,"paper_date":"2020-06-11","paper":"/paper/virtex-learning-visual-representations-from","paper_url":"https://arxiv.org/abs/2006.06666v3","paper_title":"VirTex: Learning Visual Representations from Textual Annotations","code":"https://github.com/kdexd/virtex","n_code_links":3,"official":{"repos":["kdexd/virtex"],"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":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/virtex-learning-visual-representations-from#ran","syntology_url":"https://syntology.ai/paper/2006.06666","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.06666"}}}},{"rank_in_archive_order":172,"model":"Mask R-CNN (ResNet-101 + 1 NL)","metrics":{"AP50":"63.1","AP75":"44.5","box AP":"40.8"},"uses_additional_data":false,"paper_date":"2017-11-21","paper":"/paper/non-local-neural-networks","paper_url":"http://arxiv.org/abs/1711.07971v3","paper_title":"Non-local Neural Networks","code":"https://github.com/facebookresearch/detectron","n_code_links":32,"official":{"repos":["facebookresearch/video-nonlocal-net"],"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":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":1,"n_samples":4,"n_pointer_only_licence":4,"sample_list":"/paper/non-local-neural-networks#ran","syntology_url":"https://syntology.ai/paper/1711.07971","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1711.07971"}}}},{"rank_in_archive_order":173,"model":"Mask R-CNN (ResNet-50-FPN, GroupNorm, long)","metrics":{"AP50":"61.6","AP75":"44.4","box AP":"40.8"},"uses_additional_data":false,"paper_date":"2018-03-22","paper":"/paper/group-normalization","paper_url":"http://arxiv.org/abs/1803.08494v3","paper_title":"Group Normalization","code":"https://github.com/labmlai/annotated_deep_learning_paper_implementations","n_code_links":22,"official":{"repos":["ppwwyyxx/GroupNorm-reproduce"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":7,"n_constructed":2,"n_ran_checked":5,"n_instrument":2,"n_unverified":8,"n_samples":15,"n_pointer_only_licence":5,"sample_list":"/paper/group-normalization#ran","syntology_url":"https://syntology.ai/paper/1803.08494","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1803.08494"}}}},{"rank_in_archive_order":174,"model":"RPDet (ResNet-50, multi-scale train)","metrics":{"box AP":"40.8"},"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":175,"model":"DETR-ResNet50 with iRPE-K (150 epochs)","metrics":{"box AP":"40.8"},"uses_additional_data":false,"paper_date":"2021-07-29","paper":"/paper/rethinking-and-improving-relative-position","paper_url":"https://arxiv.org/abs/2107.14222v1","paper_title":"Rethinking and Improving Relative Position Encoding for Vision Transformer","code":"https://github.com/microsoft/cream","n_code_links":1,"official":{"repos":["microsoft/cream"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]},"syntology":{"n_ran":7,"n_constructed":0,"n_ran_checked":0,"n_instrument":7,"n_unverified":2,"n_samples":9,"n_pointer_only_licence":0,"sample_list":"/paper/rethinking-and-improving-relative-position#ran","syntology_url":"https://syntology.ai/paper/2107.14222","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.14222"}}}},{"rank_in_archive_order":176,"model":"Faster R-CNN+aLRP Loss (ResNet-50, 500 scale)","metrics":{"AP50":"60.7","AP75":"43.3","box AP":"40.7"},"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":177,"model":"PPDet (ResNet-101-FPN)","metrics":{"AP50":"59.5","AP75":"44.2","APL":"52.3","APM":"44.7","APS":"25.4","box AP":"40.5"},"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":178,"model":"GCnet (ResNet-50-FPN, GRoIE)","metrics":{"AP50":"62.4","AP75":"44","APL":"52.5","APM":"44.4","APS":"24.2","box AP":"40.3"},"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":179,"model":"Mask R-CNN (ResNet-50-FPN, GroupNorm)","metrics":{"AP50":"61","AP75":"44","box AP":"40.3"},"uses_additional_data":false,"paper_date":"2018-03-22","paper":"/paper/group-normalization","paper_url":"http://arxiv.org/abs/1803.08494v3","paper_title":"Group Normalization","code":"https://github.com/labmlai/annotated_deep_learning_paper_implementations","n_code_links":22,"official":{"repos":["ppwwyyxx/GroupNorm-reproduce"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":7,"n_constructed":2,"n_ran_checked":5,"n_instrument":2,"n_unverified":8,"n_samples":15,"n_pointer_only_licence":5,"sample_list":"/paper/group-normalization#ran","syntology_url":"https://syntology.ai/paper/1803.08494","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1803.08494"}}}},{"rank_in_archive_order":180,"model":"Cascade R-CNN (ResNet-50-FPN+)","metrics":{"AP50":" 59.4","AP75":"43.7","APL":"54.1","APM":"43.7","APS":"22.9","box AP":"40.3"},"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":181,"model":"ExtremeNet (Hourglass-104, single-scale)","metrics":{"AP50":"55.1","AP75":"43.7","APL":"56.1","APM":"44.0","APS":"21.6","box AP":"40.3"},"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":182,"model":"RPDet (ResNet-101)","metrics":{"box AP":"40.3"},"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":183,"model":"RetinaNet+aLRP Loss (ResNet-50, 500 scale)","metrics":{"AP50":"60.3","AP75":"42.3","box AP":"40.2"},"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":184,"model":"Mask R-CNN (ResNet-101-FPN)","metrics":{"box AP":"40.0"},"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":185,"model":"FPN+","metrics":{"AP50":"61.3","AP75":"43.3","APL":"52.6","APM":"43.3","APS":"22.9","box AP":"39.8"},"uses_additional_data":false,"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":186,"model":"FoveaBox+aLRP Loss (ResNet-50, 500 scale)","metrics":{"AP50":"58.8","AP75":"41.5","box AP":"39.7"},"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":187,"model":"Grid R-CNN (ResNet-50-FPN)","metrics":{"AP50":"58.3","AP75":"42.4","APL":"51.5","APM":"43.8","APS":"22.6","box AP":"39.6"},"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":188,"model":"Mask R-CNN (ResNet-50, ACNet)","metrics":{"box AP":"39.5"},"uses_additional_data":false,"paper_date":"2019-04-07","paper":"/paper/adaptively-connected-neural-networks","paper_url":"http://arxiv.org/abs/1904.03579v1","paper_title":"Adaptively Connected Neural Networks","code":"https://github.com/wanggrun/Adaptively-Connected-Neural-Networks","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":189,"model":"FSAF (ResNet-101, anchor-based branches)","metrics":{"AP50":"59.2","box AP":"39.3"},"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":190,"model":"Mask R-CNN (HRNetV2p-W18)","metrics":{"APL":"51.0","APM":"41.7","box AP":"39.2"},"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":191,"model":"Mask R-CNN (ResNet-50 + 1 NL)","metrics":{"AP50":"61.1","AP75":"41.9","box AP":"39.0"},"uses_additional_data":false,"paper_date":"2017-11-21","paper":"/paper/non-local-neural-networks","paper_url":"http://arxiv.org/abs/1711.07971v3","paper_title":"Non-local Neural Networks","code":"https://github.com/facebookresearch/detectron","n_code_links":32,"official":{"repos":["facebookresearch/video-nonlocal-net"],"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":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":1,"n_samples":4,"n_pointer_only_licence":4,"sample_list":"/paper/non-local-neural-networks#ran","syntology_url":"https://syntology.ai/paper/1711.07971","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1711.07971"}}}},{"rank_in_archive_order":192,"model":"FoveaBox (ResNet-101-FPN, 800x800)","metrics":{"AP50":"58.4","AP75":"41.5","APL":"51.7","APM":"43.5","APS":"22.3","box AP":"38.9"},"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":193,"model":"FCOS (ResNet-50-FPN + improvements)","metrics":{"AP50":"57.4","AP75":"41.4","APL":"49.8","APM":"42.5","APS":"22.3","box AP":"38.6 "},"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":194,"model":"RPDet (ResNet-50)","metrics":{"box AP":"38.6"},"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":195,"model":"Libra R-CNN (ResNet-50 FPN)","metrics":{"AP50":"59.3","AP75":"42.0","APL":"50.5","APM":"42.1","APS":"22.9","box AP":"38.5"},"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":196,"model":"Mask R-CNN (ResNet-50-FPN, GRoIE)","metrics":{"AP50":"59.9","AP75":"41.7","APL":"49.7","APM":"42.1","APS":"22.9","box AP":"38.4"},"uses_additional_data":false,"paper_date":"2020-04-28","paper":"/paper/a-novel-region-of-interest-extraction-layer","paper_url":"https://arxiv.org/abs/2004.13665v2","paper_title":"A novel Region of Interest Extraction Layer for Instance Segmentation","code":"https://github.com/open-mmlab/mmdetection","n_code_links":5,"official":null,"syntology":null},{"rank_in_archive_order":197,"model":"CornerNet511 (Hourglass-104)","metrics":{"AP50":"53.8","AP75":"40.9","APL":"51.8","APM":"40.5","APS":"18.6","box AP":"38.4"},"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":198,"model":"FoveaBox+Retina (ResNet-50)","metrics":{"AP50":"57.8","AP75":"40.5","box AP":"38.1"},"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":199,"model":"Faster R-CNN (HRNetV2p-W18)","metrics":{"AP50":"58.9","AP75":"41.5","APL":"49.6","APM":"40.8","APS":"22.6","box AP":"38.0"},"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":200,"model":"FoveaBox (ResNet-101-FPN, 600x600)","metrics":{"AP50":"57.8","AP75":"40.2","APL":"52.7","APM":"42.2","APS":"19.5","box AP":"38"},"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":201,"model":"FSAF (ResNet-101)","metrics":{"AP50":"58.0","box AP":"37.9"},"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":202,"model":"Mask R-CNN (ResNet-50-FPN)","metrics":{"box AP":"37.7"},"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":203,"model":"Faster R-CNN (ResNet-50-FPN, GRoIE)","metrics":{"AP50":"59.2","AP75":"40.6","APL":"47.8","APM":"41.5","APS":"22.3","box AP":"37.5"},"uses_additional_data":false,"paper_date":"2020-04-28","paper":"/paper/a-novel-region-of-interest-extraction-layer","paper_url":"https://arxiv.org/abs/2004.13665v2","paper_title":"A novel Region of Interest Extraction Layer for Instance Segmentation","code":"https://github.com/open-mmlab/mmdetection","n_code_links":5,"official":null,"syntology":null},{"rank_in_archive_order":204,"model":"Mask R-CNN (ResNeXt-101-FPN)","metrics":{"AP50":"59.5","AP75":"38.9","box AP":"36.7"},"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":205,"model":"FoveaBox (ResNet-50-FPN, 600x600)","metrics":{"AP50":"55.2","AP75":"37.9","APL":"50.5","APM":"39.4","APS":"18.6","box AP":"36.0"},"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":206,"model":"FSAF (ResNet-50)","metrics":{"AP50":"55.0","AP75":"37.9","APL":"48.2","APM":"39.6","APS":"19.8","box AP":"35.9"},"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":207,"model":"GHM-C + GHM-R (RetinaNet-FPN-ResNet-50, M=30)","metrics":{"AP50":"55.5","AP75":"38.1","APL":"46.7","APM":"39.6","APS":"19.6","box AP":"35.8"},"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":208,"model":"Online Fg Bal. Sampling+Hard Negative Mining (ResNet-50)","metrics":{"AP50":"55.3","box AP":"35.6"},"uses_additional_data":false,"paper_date":"2019-09-21","paper":"/paper/190909777","paper_url":"https://arxiv.org/abs/1909.09777v3","paper_title":"Generating Positive Bounding Boxes for Balanced Training of Object Detectors","code":"https://github.com/kemaloksuz/BoundingBoxGenerator","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":209,"model":"M2Det (ResNet-1o1, 320x320)","metrics":{"AP50":"53.7","APL":"49.3","APM":"39.5","APS":"15.9","box AP":"34.1"},"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":210,"model":"Faster R-CNN (Res2Net-50)","metrics":{"AP50":"53.6","APL":"51.1","APM":"38.3","APS":"14","box AP":"33.7"},"uses_additional_data":false,"paper_date":"2019-04-02","paper":"/paper/res2net-a-new-multi-scale-backbone","paper_url":"https://arxiv.org/abs/1904.01169v3","paper_title":"Res2Net: A New Multi-scale Backbone Architecture","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":34,"official":null,"syntology":{"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":4,"n_samples":9,"n_pointer_only_licence":9,"sample_list":"/paper/res2net-a-new-multi-scale-backbone#ran","syntology_url":"https://syntology.ai/paper/1904.01169","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.01169"}}}},{"rank_in_archive_order":211,"model":"M2Det (VGG-16, 320x320)","metrics":{"AP50":"52.2","APL":"49.1","APM":"38.2","APS":"15","box AP":"33.2"},"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":212,"model":"SOLQ (Swin-L, single scale)","metrics":{"AP50":"74.9","AP75":"61.3","APL":"71.9"},"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":213,"model":"YOLOR-D6 (1280, single-scale, 31 fps)","metrics":{"AP50":"73.5","AP75":"60.6","APL":"68.7","APM":"60.1","APS":"40.4"},"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":214,"model":"EfficientDet-D7x (single-scale)","metrics":{"AP50":"73.4","AP75":"59.0","APL":"67.9","APM":"58.0","APS":"40.0"},"uses_additional_data":false,"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":215,"model":"YOLOR-P6 (1280, single-scale, 72 fps)","metrics":{"AP50":"70.6","AP75":"57.4","APL":"65.2","APM":"57.3","APS":"37.4"},"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":216,"model":"FocalNet-T (SRF, Cascade Mask R-CNN)","metrics":{"AP50":"70.1","AP75":"55.8"},"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":217,"model":"R3-CNN (ResNet-50-FPN, GRoIE)","metrics":{"AP50":"61.2","AP75":"45.6","APS":"24.4"},"uses_additional_data":false,"paper_date":"2021-04-03","paper":"/paper/recursively-refined-r-cnn-instance","paper_url":"https://arxiv.org/abs/2104.01329v2","paper_title":"Recursively Refined R-CNN: Instance Segmentation with Self-RoI Rebalancing","code":"https://github.com/IMPLabUniPr/mmdetection","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":218,"model":"Mask R-CNN (HRNetV2p-W32, cascade)","metrics":{"APM":"47.9","APS":"26.1"},"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":219,"model":"Shift-T","metrics":{"APM":"42.3"},"uses_additional_data":false,"paper_date":"2022-01-26","paper":"/paper/when-shift-operation-meets-vision-transformer","paper_url":"https://arxiv.org/abs/2201.10801v1","paper_title":"When Shift Operation Meets Vision Transformer: An Extremely Simple Alternative to Attention Mechanism","code":"https://github.com/keras-team/keras-io/blob/master/examples/vision/shiftvit.py","n_code_links":2,"official":{"repos":["microsoft/SPACH"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":6,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]},"syntology":{"n_ran":6,"n_constructed":6,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_samples":7,"n_pointer_only_licence":0,"sample_list":"/paper/when-shift-operation-meets-vision-transformer#ran","syntology_url":"https://syntology.ai/paper/2201.10801","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.10801"}}}},{"rank_in_archive_order":220,"model":"DyHead (ResNeXt-64x4d-101-DCN, multi scale)","metrics":{"APL":"66.3"},"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"}}}}],"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), 1 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 1,595 of the 8,888 were already full without this board, so if it was crowded out of them it is not counted), and 1 proposed a result, which gave no cell that passed the extractor's own checks; 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":220,"metric_columns":7,"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":1595,"candidates":1,"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":1,"no_cell_passed_checks":1,"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; 1 newer paper judged to report on this board so far"},"judged_to_report":{"heading":"Newer papers whose tables Claude Sonnet 4.5 judged to report on this benchmark (a model's judgement, not a result; newest first by arXiv id)","judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"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":1,"shown_on_page":1,"no_cell_split":{"no_cell_passed_checks_in_ledger":1,"rows_refused_by_rule":1,"rows_no_cell_passed_checks":0},"rows":[{"arxiv_id":"2604.14724","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric"}]},"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":147,"rows_with_any_sample_ran":146,"rows_with_a_run_with_no_instrument_failure":134,"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":112,"rows_whose_official_repository_has_a_sample_that_ran":66,"rows_whose_official_repository_has_a_run_with_no_instrument_failure":56,"rows_community_repositories_only":31,"rows_runs_from_other_or_unrecorded_repositories":9,"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":66,"distinct_papers_with_any_sample_ran":65,"distinct_papers_with_a_run_with_no_instrument_failure":57,"samples_over_distinct_papers":{"n_ran":1136,"n_constructed":322,"n_ran_checked":807,"n_instrument":329,"n_unverified":542,"n_samples":1678,"n_pointer_only_licence":565,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":2856,"n_constructed":753,"n_ran_checked":2012,"n_instrument":844,"n_unverified":1395,"n_samples":4251,"n_pointer_only_licence":1634,"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":"0895f5d2d621d71216a32119df83610621e3b84556c2611255e333b506dc945e","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}