{"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/instance-segmentation-on-coco","task":{"name":"Instance Segmentation","url":"/task/instance-segmentation","note":null},"dataset":{"name":"COCO test-dev","url":"/dataset/coco"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"**Instance Segmentation** is a computer vision task that involves identifying and separating individual objects within an image, including detecting the boundaries of each object and assigning a unique label to each object. The goal of instance segmentation is to produce a pixel-wise segmentation map of the image, where each pixel is assigned to a specific object instance.\r\n\r\nImage Credit: [Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers, CVPR'21](https://github.com/lkeab/BCNet)","description_from":"task","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":["mask AP","AP50","AP75","APS","APM","APL"],"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":{"mask AP":"higher","AP50":null,"AP75":null,"APS":null,"APM":null,"APL":null}},"counts":{"rows":112,"rows_with_code":107,"rows_with_paper_page":112,"rows_dated":112,"rows_using_additional_data":20},"rows":[{"rank_in_archive_order":1,"model":"Co-DETR","metrics":{"AP50":"80.2","AP75":"63.4","APL":"72.0","APM":"60.1","APS":"41.6","mask AP":"57.1"},"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":2,"model":"CBNetV2 (EVA02, single-scale)","metrics":{"AP50":"80.3","AP75":"62.1","APL":"70.9","APM":"59.3","APS":"39.7","mask AP":"56.1"},"uses_additional_data":true,"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":3,"model":"EVA","metrics":{"AP50":"80.0","APL":"72.4","APM":"58.0","APS":"36.3","mask AP":"55.5"},"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":4,"model":"FD-SwinV2-G","metrics":{"mask AP":"55.4"},"uses_additional_data":true,"paper_date":"2022-05-27","paper":"/paper/contrastive-learning-rivals-masked-image","paper_url":"https://arxiv.org/abs/2205.14141v3","paper_title":"Contrastive Learning Rivals Masked Image Modeling in Fine-tuning via Feature Distillation","code":"https://github.com/SwinTransformer/Feature-Distillation","n_code_links":1,"official":{"repos":["SwinTransformer/Feature-Distillation"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":5,"ran_from_kinds":["official"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":5,"n_samples":8,"n_pointer_only_licence":8,"sample_list":"/paper/contrastive-learning-rivals-masked-image#ran","syntology_url":"https://syntology.ai/paper/2205.14141","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.14141"}}}},{"rank_in_archive_order":5,"model":"Mask Frozen-DETR","metrics":{"AP50":"79.3","AP75":"61.4","APL":"70.4","APM":"58.4","APS":"37.8","mask AP":"55.3"},"uses_additional_data":true,"paper_date":"2023-08-07","paper":"/paper/mask-frozen-detr-high-quality-instance","paper_url":"https://arxiv.org/abs/2308.03747v1","paper_title":"Mask Frozen-DETR: High Quality Instance Segmentation with One GPU","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":6,"model":"BEiT-3","metrics":{"mask AP":"54.8"},"uses_additional_data":false,"paper_date":"2022-08-22","paper":"/paper/image-as-a-foreign-language-beit-pretraining","paper_url":"https://arxiv.org/abs/2208.10442v2","paper_title":"Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Tasks","code":"https://github.com/microsoft/unilm/tree/master/beit","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":7,"model":"MasK DINO (SwinL, multi-scale)","metrics":{"mask AP":"54.7"},"uses_additional_data":true,"paper_date":"2022-06-06","paper":"/paper/mask-dino-towards-a-unified-transformer-based-1","paper_url":"https://arxiv.org/abs/2206.02777v3","paper_title":"Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segmentation","code":"https://github.com/PaddlePaddle/PaddleDetection","n_code_links":10,"official":{"repos":["idea-research/maskdino"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":11,"n_constructed":0,"n_ran_checked":2,"n_instrument":9,"n_unverified":2,"n_samples":13,"n_pointer_only_licence":13,"sample_list":"/paper/mask-dino-towards-a-unified-transformer-based-1#ran","syntology_url":"https://syntology.ai/paper/2206.02777","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.02777"}}}},{"rank_in_archive_order":8,"model":"ViT-Adapter-L (HTC++, BEiTv2, O365, multi-scale)","metrics":{"mask AP":"54.5"},"uses_additional_data":true,"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":9,"model":"GLEE-Pro","metrics":{"mask AP":"54.5"},"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":10,"model":"SwinV2-G (HTC++)","metrics":{"mask AP":"54.4"},"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":11,"model":"GLEE-Plus","metrics":{"mask AP":"53.3"},"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":12,"model":"Soft Teacher + Swin-L (HTC++, multi-scale)","metrics":{"mask AP":"53.0"},"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":13,"model":"ViT-Adapter-L (HTC++, BEiTv2 pretrain, multi-scale)","metrics":{"mask AP":"53.0"},"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":14,"model":"Mask DINO (SwinL, single -scale)","metrics":{"mask AP":"52.8"},"uses_additional_data":false,"paper_date":"2022-06-06","paper":"/paper/mask-dino-towards-a-unified-transformer-based-1","paper_url":"https://arxiv.org/abs/2206.02777v3","paper_title":"Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segmentation","code":"https://github.com/PaddlePaddle/PaddleDetection","n_code_links":10,"official":{"repos":["idea-research/maskdino"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":11,"n_constructed":0,"n_ran_checked":2,"n_instrument":9,"n_unverified":2,"n_samples":13,"n_pointer_only_licence":13,"sample_list":"/paper/mask-dino-towards-a-unified-transformer-based-1#ran","syntology_url":"https://syntology.ai/paper/2206.02777","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.02777"}}}},{"rank_in_archive_order":15,"model":"ViT-Adapter-L (HTC++, BEiT pretrain, multi-scale)","metrics":{"mask AP":"52.5"},"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":16,"model":"CBNetV2 (Dual-Swin-L HTC, multi-scale)","metrics":{"mask AP":"52.3"},"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":17,"model":"UNINEXT-H","metrics":{"AP50":"76.2","AP75":"56.7","APL":"67.5","APM":"55.9","APS":"33.3","mask AP":"51.8"},"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":18,"model":"CBNetV2 (Dual-Swin-L HTC, single-scale)","metrics":{"mask AP":"51.6"},"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":19,"model":"Focal-L (HTC++, multi-scale)","metrics":{"AP50":"75.4","AP75":"56.5","APL":"64.2","APS":"35.6","mask AP":"51.3"},"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":20,"model":"Swin-L (HTC++, multi scale)","metrics":{"mask AP":"51.1"},"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":21,"model":"Mask2Former (Swin-L, single scale)","metrics":{"AP50":"74.9","AP75":"54.9","APL":"71.2","APM":"53.8","APS":"29.1","mask AP":"50.5"},"uses_additional_data":false,"paper_date":"2021-12-02","paper":"/paper/masked-attention-mask-transformer-for","paper_url":"https://arxiv.org/abs/2112.01527v3","paper_title":"Masked-attention Mask Transformer for Universal Image Segmentation","code":"https://github.com/huggingface/transformers","n_code_links":7,"official":{"repos":["facebookresearch/Mask2Former"],"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":7,"n_constructed":0,"n_ran_checked":1,"n_instrument":6,"n_unverified":1,"n_samples":8,"n_pointer_only_licence":0,"sample_list":"/paper/masked-attention-mask-transformer-for#ran","syntology_url":"https://syntology.ai/paper/2112.01527","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.01527"}}}},{"rank_in_archive_order":22,"model":"Swin-L (HTC++, single scale)","metrics":{"mask AP":"50.2"},"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":23,"model":"ISTR-SMT (Swin-L, single scale)","metrics":{"mask AP":"49.7"},"uses_additional_data":false,"paper_date":"2021-05-03","paper":"/paper/istr-end-to-end-instance-segmentation-with","paper_url":"https://arxiv.org/abs/2105.00637v2","paper_title":"ISTR: End-to-End Instance Segmentation with Transformers","code":"https://github.com/hujiecpp/ISTR","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":24,"model":"QueryInst (single scale)","metrics":{"AP50":"74.2","AP75":"53.8","APL":"63.2","APM":"51.8","APS":"31.5","mask AP":"49.1"},"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":25,"model":"Cascade Eff-B7 NAS-FPN (1280, self-training Copy Paste, single-scale)","metrics":{"mask AP":"49.1"},"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":26,"model":"dBOT ViT-L (CLIP)","metrics":{"mask AP":"48.8"},"uses_additional_data":false,"paper_date":"2022-09-08","paper":"/paper/exploring-target-representations-for-masked","paper_url":"https://arxiv.org/abs/2209.03917v3","paper_title":"Exploring Target Representations for Masked Autoencoders","code":"https://github.com/liuxingbin/dbot","n_code_links":1,"official":{"repos":["liuxingbin/dbot"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":2,"ran_from_kinds":["official"]},"syntology":{"n_ran":11,"n_constructed":0,"n_ran_checked":10,"n_instrument":1,"n_unverified":2,"n_samples":13,"n_pointer_only_licence":2,"sample_list":"/paper/exploring-target-representations-for-masked#ran","syntology_url":"https://syntology.ai/paper/2209.03917","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.03917"}}}},{"rank_in_archive_order":27,"model":"MogaNet-XL (Cascade Mask R-CNN)","metrics":{"mask AP":"48.8"},"uses_additional_data":false,"paper_date":"2022-11-07","paper":"/paper/efficient-multi-order-gated-aggregation","paper_url":"https://arxiv.org/abs/2211.03295v3","paper_title":"MogaNet: Multi-order Gated Aggregation Network","code":"https://github.com/chengtan9907/OpenSTL","n_code_links":7,"official":{"repos":["Westlake-AI/MogaNet","Westlake-AI/openmixup","chengtan9907/OpenSTL"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":7,"n_ran_no_instrument_failure":10,"n_unverified":3,"ran_from_kinds":["official"]},"syntology":{"n_ran":12,"n_constructed":7,"n_ran_checked":10,"n_instrument":2,"n_unverified":3,"n_samples":15,"n_pointer_only_licence":0,"sample_list":"/paper/efficient-multi-order-gated-aggregation#ran","syntology_url":"https://syntology.ai/paper/2211.03295","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.03295"}}}},{"rank_in_archive_order":28,"model":"DetectoRS (ResNeXt-101-64x4d, multi-scale)","metrics":{"AP50":"72.0","AP75":"53.3","APL":"61.5","APM":"50.9","APS":"31.6","mask AP":"48.5"},"uses_additional_data":false,"paper_date":"2020-06-03","paper":"/paper/detectors-detecting-objects-with-recursive-1","paper_url":"https://arxiv.org/abs/2006.02334v2","paper_title":"DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolution","code":"https://github.com/open-mmlab/mmdetection","n_code_links":6,"official":{"repos":["joe-siyuan-qiao/DetectoRS"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_samples":4,"n_pointer_only_licence":0,"sample_list":"/paper/detectors-detecting-objects-with-recursive-1#ran","syntology_url":"https://syntology.ai/paper/2006.02334","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.02334"}}}},{"rank_in_archive_order":29,"model":"dBOT ViT-L","metrics":{"mask AP":"48.3"},"uses_additional_data":false,"paper_date":"2022-09-08","paper":"/paper/exploring-target-representations-for-masked","paper_url":"https://arxiv.org/abs/2209.03917v3","paper_title":"Exploring Target Representations for Masked Autoencoders","code":"https://github.com/liuxingbin/dbot","n_code_links":1,"official":{"repos":["liuxingbin/dbot"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":2,"ran_from_kinds":["official"]},"syntology":{"n_ran":11,"n_constructed":0,"n_ran_checked":10,"n_instrument":1,"n_unverified":2,"n_samples":13,"n_pointer_only_licence":2,"sample_list":"/paper/exploring-target-representations-for-masked#ran","syntology_url":"https://syntology.ai/paper/2209.03917","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.03917"}}}},{"rank_in_archive_order":30,"model":"DiffusionInst-SwinL","metrics":{"mask AP":"48.3"},"uses_additional_data":false,"paper_date":"2022-12-06","paper":"/paper/diffusioninst-diffusion-model-for-instance","paper_url":"https://arxiv.org/abs/2212.02773v3","paper_title":"DiffusionInst: Diffusion Model for Instance Segmentation","code":"https://github.com/chenhaoxing/DiffusionInst","n_code_links":2,"official":{"repos":["chenhaoxing/DiffusionInst"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]},"syntology":{"n_ran":12,"n_constructed":0,"n_ran_checked":6,"n_instrument":6,"n_unverified":4,"n_samples":16,"n_pointer_only_licence":7,"sample_list":"/paper/diffusioninst-diffusion-model-for-instance#ran","syntology_url":"https://syntology.ai/paper/2212.02773","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.02773"}}}},{"rank_in_archive_order":31,"model":"GLEE-Lite","metrics":{"mask AP":"48.3"},"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":32,"model":"DiffusionInst-SwinB","metrics":{"mask AP":"47.6"},"uses_additional_data":false,"paper_date":"2022-12-06","paper":"/paper/diffusioninst-diffusion-model-for-instance","paper_url":"https://arxiv.org/abs/2212.02773v3","paper_title":"DiffusionInst: Diffusion Model for Instance Segmentation","code":"https://github.com/chenhaoxing/DiffusionInst","n_code_links":2,"official":{"repos":["chenhaoxing/DiffusionInst"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]},"syntology":{"n_ran":12,"n_constructed":0,"n_ran_checked":6,"n_instrument":6,"n_unverified":4,"n_samples":16,"n_pointer_only_licence":7,"sample_list":"/paper/diffusioninst-diffusion-model-for-instance#ran","syntology_url":"https://syntology.ai/paper/2212.02773","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.02773"}}}},{"rank_in_archive_order":33,"model":"DetectoRS (ResNeXt-101-32x4d, multi-scale)","metrics":{"AP50":"71.1","AP75":"51.6","APL":"59.6","APM":"49.5","APS":"30.3","mask AP":"47.1"},"uses_additional_data":false,"paper_date":"2020-06-03","paper":"/paper/detectors-detecting-objects-with-recursive-1","paper_url":"https://arxiv.org/abs/2006.02334v2","paper_title":"DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolution","code":"https://github.com/open-mmlab/mmdetection","n_code_links":6,"official":{"repos":["joe-siyuan-qiao/DetectoRS"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_samples":4,"n_pointer_only_licence":0,"sample_list":"/paper/detectors-detecting-objects-with-recursive-1#ran","syntology_url":"https://syntology.ai/paper/2006.02334","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.02334"}}}},{"rank_in_archive_order":34,"model":"Cascade Eff-B7 NAS-FPN (1280)","metrics":{"mask AP":"46.9"},"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":35,"model":"SOLQ (Swin-L, single scale)","metrics":{"mask AP":"46.7"},"uses_additional_data":false,"paper_date":"2021-06-04","paper":"/paper/solq-segmenting-objects-by-learning-queries","paper_url":"https://arxiv.org/abs/2106.02351v3","paper_title":"SOLQ: Segmenting Objects by Learning Queries","code":"https://github.com/megvii-research/SOLQ","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":36,"model":"dBOT ViT-B","metrics":{"mask AP":"46.3"},"uses_additional_data":false,"paper_date":"2022-09-08","paper":"/paper/exploring-target-representations-for-masked","paper_url":"https://arxiv.org/abs/2209.03917v3","paper_title":"Exploring Target Representations for Masked Autoencoders","code":"https://github.com/liuxingbin/dbot","n_code_links":1,"official":{"repos":["liuxingbin/dbot"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":2,"ran_from_kinds":["official"]},"syntology":{"n_ran":11,"n_constructed":0,"n_ran_checked":10,"n_instrument":1,"n_unverified":2,"n_samples":13,"n_pointer_only_licence":2,"sample_list":"/paper/exploring-target-representations-for-masked#ran","syntology_url":"https://syntology.ai/paper/2209.03917","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.03917"}}}},{"rank_in_archive_order":37,"model":"dBOT ViT-B (CLIP)","metrics":{"mask AP":"46.2"},"uses_additional_data":false,"paper_date":"2022-09-08","paper":"/paper/exploring-target-representations-for-masked","paper_url":"https://arxiv.org/abs/2209.03917v3","paper_title":"Exploring Target Representations for Masked Autoencoders","code":"https://github.com/liuxingbin/dbot","n_code_links":1,"official":{"repos":["liuxingbin/dbot"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":2,"ran_from_kinds":["official"]},"syntology":{"n_ran":11,"n_constructed":0,"n_ran_checked":10,"n_instrument":1,"n_unverified":2,"n_samples":13,"n_pointer_only_licence":2,"sample_list":"/paper/exploring-target-representations-for-masked#ran","syntology_url":"https://syntology.ai/paper/2209.03917","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.03917"}}}},{"rank_in_archive_order":38,"model":"Mask R-CNN (SpineNet-190, 1536x1536)","metrics":{"mask AP":"46.1"},"uses_additional_data":false,"paper_date":"2019-12-10","paper":"/paper/spinenet-learning-scale-permuted-backbone-for","paper_url":"https://arxiv.org/abs/1912.05027v3","paper_title":"SpineNet: Learning Scale-Permuted Backbone for Recognition and Localization","code":"https://github.com/tensorflow/models/tree/master/official/vision/beta/modeling/backbones","n_code_links":13,"official":null,"syntology":null},{"rank_in_archive_order":39,"model":"MogaNet-L (Cascade Mask R-CNN)","metrics":{"mask AP":"46.1"},"uses_additional_data":false,"paper_date":"2022-11-07","paper":"/paper/efficient-multi-order-gated-aggregation","paper_url":"https://arxiv.org/abs/2211.03295v3","paper_title":"MogaNet: Multi-order Gated Aggregation Network","code":"https://github.com/chengtan9907/OpenSTL","n_code_links":7,"official":{"repos":["Westlake-AI/MogaNet","Westlake-AI/openmixup","chengtan9907/OpenSTL"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":7,"n_ran_no_instrument_failure":10,"n_unverified":3,"ran_from_kinds":["official"]},"syntology":{"n_ran":12,"n_constructed":7,"n_ran_checked":10,"n_instrument":2,"n_unverified":3,"n_samples":15,"n_pointer_only_licence":0,"sample_list":"/paper/efficient-multi-order-gated-aggregation#ran","syntology_url":"https://syntology.ai/paper/2211.03295","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.03295"}}}},{"rank_in_archive_order":40,"model":"MogaNet-B (Cascade Mask R-CNN)","metrics":{"mask AP":"46"},"uses_additional_data":false,"paper_date":"2022-11-07","paper":"/paper/efficient-multi-order-gated-aggregation","paper_url":"https://arxiv.org/abs/2211.03295v3","paper_title":"MogaNet: Multi-order Gated Aggregation Network","code":"https://github.com/chengtan9907/OpenSTL","n_code_links":7,"official":{"repos":["Westlake-AI/MogaNet","Westlake-AI/openmixup","chengtan9907/OpenSTL"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":7,"n_ran_no_instrument_failure":10,"n_unverified":3,"ran_from_kinds":["official"]},"syntology":{"n_ran":12,"n_constructed":7,"n_ran_checked":10,"n_instrument":2,"n_unverified":3,"n_samples":15,"n_pointer_only_licence":0,"sample_list":"/paper/efficient-multi-order-gated-aggregation#ran","syntology_url":"https://syntology.ai/paper/2211.03295","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.03295"}}}},{"rank_in_archive_order":41,"model":"Swin-B + Cascade Mask R-CNN (tri-layer modelling)","metrics":{"mask AP":"45.9"},"uses_additional_data":false,"paper_date":"2022-10-18","paper":"/paper/a-tri-layer-plugin-to-improve-occluded","paper_url":"https://arxiv.org/abs/2210.10046v1","paper_title":"A Tri-Layer Plugin to Improve Occluded Detection","code":"https://github.com/Championchess/Tri-Layer_Plugin_Occluded_Detection","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":42,"model":"GCNet (ResNeXt-101 + DCN + cascade + GC r4)","metrics":{"AP50":"68.9","AP75":"49.6","mask AP":"45.4"},"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":43,"model":"MogaNet-S (Cascade Mask R-CNN)","metrics":{"mask AP":"45.1"},"uses_additional_data":false,"paper_date":"2022-11-07","paper":"/paper/efficient-multi-order-gated-aggregation","paper_url":"https://arxiv.org/abs/2211.03295v3","paper_title":"MogaNet: Multi-order Gated Aggregation Network","code":"https://github.com/chengtan9907/OpenSTL","n_code_links":7,"official":{"repos":["Westlake-AI/MogaNet","Westlake-AI/openmixup","chengtan9907/OpenSTL"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":7,"n_ran_no_instrument_failure":10,"n_unverified":3,"ran_from_kinds":["official"]},"syntology":{"n_ran":12,"n_constructed":7,"n_ran_checked":10,"n_instrument":2,"n_unverified":3,"n_samples":15,"n_pointer_only_licence":0,"sample_list":"/paper/efficient-multi-order-gated-aggregation#ran","syntology_url":"https://syntology.ai/paper/2211.03295","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.03295"}}}},{"rank_in_archive_order":44,"model":"gSwin-S","metrics":{"mask AP":"45.03"},"uses_additional_data":false,"paper_date":"2022-08-24","paper":"/paper/gswin-gated-mlp-vision-model-with","paper_url":"https://arxiv.org/abs/2208.11718v1","paper_title":"gSwin: Gated MLP Vision Model with Hierarchical Structure of Shifted Window","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":45,"model":"iBOT (ViT-B/16)","metrics":{"mask AP":"44.2"},"uses_additional_data":true,"paper_date":"2021-11-15","paper":"/paper/ibot-image-bert-pre-training-with-online","paper_url":"https://arxiv.org/abs/2111.07832v3","paper_title":"iBOT: Image BERT Pre-Training with Online Tokenizer","code":"https://github.com/bytedance/ibot","n_code_links":2,"official":{"repos":["bytedance/ibot"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]},"syntology":{"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0,"sample_list":"/paper/ibot-image-bert-pre-training-with-online#ran","syntology_url":"https://syntology.ai/paper/2111.07832","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.07832"}}}},{"rank_in_archive_order":46,"model":"gSwin-T","metrics":{"mask AP":"44.16"},"uses_additional_data":false,"paper_date":"2022-08-24","paper":"/paper/gswin-gated-mlp-vision-model-with","paper_url":"https://arxiv.org/abs/2208.11718v1","paper_title":"gSwin: Gated MLP Vision Model with Hierarchical Structure of Shifted Window","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":47,"model":"MogaNet-L (Mask R-CNN 1x)","metrics":{"mask AP":"44.1"},"uses_additional_data":false,"paper_date":"2022-11-07","paper":"/paper/efficient-multi-order-gated-aggregation","paper_url":"https://arxiv.org/abs/2211.03295v3","paper_title":"MogaNet: Multi-order Gated Aggregation Network","code":"https://github.com/chengtan9907/OpenSTL","n_code_links":7,"official":{"repos":["Westlake-AI/MogaNet","Westlake-AI/openmixup","chengtan9907/OpenSTL"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":7,"n_ran_no_instrument_failure":10,"n_unverified":3,"ran_from_kinds":["official"]},"syntology":{"n_ran":12,"n_constructed":7,"n_ran_checked":10,"n_instrument":2,"n_unverified":3,"n_samples":15,"n_pointer_only_licence":0,"sample_list":"/paper/efficient-multi-order-gated-aggregation#ran","syntology_url":"https://syntology.ai/paper/2211.03295","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.03295"}}}},{"rank_in_archive_order":48,"model":"A2MIM (ViT-B)","metrics":{"mask AP":"43.5"},"uses_additional_data":false,"paper_date":"2022-05-27","paper":"/paper/architecture-agnostic-masked-image-modeling","paper_url":"https://arxiv.org/abs/2205.13943v4","paper_title":"Architecture-Agnostic Masked Image Modeling -- From ViT back to CNN","code":"https://github.com/open-mmlab/mmpretrain","n_code_links":3,"official":null,"syntology":null},{"rank_in_archive_order":49,"model":"Cascade Mask R-CNN (ResNeXt152, CBNet)","metrics":{"mask AP":"43.3"},"uses_additional_data":false,"paper_date":"2019-09-09","paper":"/paper/cbnet-a-novel-composite-backbone-network","paper_url":"https://arxiv.org/abs/1909.03625v1","paper_title":"CBNet: A Novel Composite Backbone Network Architecture for Object Detection","code":"https://github.com/open-mmlab/mmdetection","n_code_links":6,"official":{"repos":["PKUbahuangliuhe/CBNet"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":2,"n_samples":4,"n_pointer_only_licence":1,"sample_list":"/paper/cbnet-a-novel-composite-backbone-network#ran","syntology_url":"https://syntology.ai/paper/1909.03625","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.03625"}}}},{"rank_in_archive_order":50,"model":"MogaNet-B (Mask R-CNN 1x)","metrics":{"mask AP":"43.2"},"uses_additional_data":false,"paper_date":"2022-11-07","paper":"/paper/efficient-multi-order-gated-aggregation","paper_url":"https://arxiv.org/abs/2211.03295v3","paper_title":"MogaNet: Multi-order Gated Aggregation Network","code":"https://github.com/chengtan9907/OpenSTL","n_code_links":7,"official":{"repos":["Westlake-AI/MogaNet","Westlake-AI/openmixup","chengtan9907/OpenSTL"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":7,"n_ran_no_instrument_failure":10,"n_unverified":3,"ran_from_kinds":["official"]},"syntology":{"n_ran":12,"n_constructed":7,"n_ran_checked":10,"n_instrument":2,"n_unverified":3,"n_samples":15,"n_pointer_only_licence":0,"sample_list":"/paper/efficient-multi-order-gated-aggregation#ran","syntology_url":"https://syntology.ai/paper/2211.03295","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.03295"}}}},{"rank_in_archive_order":51,"model":"ResNeSt101","metrics":{"mask AP":"43%"},"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":52,"model":"gSwin-VT","metrics":{"mask AP":"42.87"},"uses_additional_data":false,"paper_date":"2022-08-24","paper":"/paper/gswin-gated-mlp-vision-model-with","paper_url":"https://arxiv.org/abs/2208.11718v1","paper_title":"gSwin: Gated MLP Vision Model with Hierarchical Structure of Shifted Window","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":53,"model":"iBOT (ViT-S/16)","metrics":{"mask AP":"42.6"},"uses_additional_data":true,"paper_date":"2021-11-15","paper":"/paper/ibot-image-bert-pre-training-with-online","paper_url":"https://arxiv.org/abs/2111.07832v3","paper_title":"iBOT: Image BERT Pre-Training with Online Tokenizer","code":"https://github.com/bytedance/ibot","n_code_links":2,"official":{"repos":["bytedance/ibot"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]},"syntology":{"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0,"sample_list":"/paper/ibot-image-bert-pre-training-with-online#ran","syntology_url":"https://syntology.ai/paper/2111.07832","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.07832"}}}},{"rank_in_archive_order":54,"model":"Mask Transfiner(ResNet101-FPN)","metrics":{"mask AP":"42.2"},"uses_additional_data":false,"paper_date":"2021-11-26","paper":"/paper/mask-transfiner-for-high-quality-instance","paper_url":"https://arxiv.org/abs/2111.13673v1","paper_title":"Mask Transfiner for High-Quality Instance Segmentation","code":"https://github.com/SysCV/transfiner","n_code_links":1,"official":{"repos":["SysCV/transfiner"],"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/mask-transfiner-for-high-quality-instance#ran","syntology_url":"https://syntology.ai/paper/2111.13673","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.13673"}}}},{"rank_in_archive_order":55,"model":"MogaNet-S (Mask R-CNN 1x)","metrics":{"mask AP":"42.2"},"uses_additional_data":false,"paper_date":"2022-11-07","paper":"/paper/efficient-multi-order-gated-aggregation","paper_url":"https://arxiv.org/abs/2211.03295v3","paper_title":"MogaNet: Multi-order Gated Aggregation Network","code":"https://github.com/chengtan9907/OpenSTL","n_code_links":7,"official":{"repos":["Westlake-AI/MogaNet","Westlake-AI/openmixup","chengtan9907/OpenSTL"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":7,"n_ran_no_instrument_failure":10,"n_unverified":3,"ran_from_kinds":["official"]},"syntology":{"n_ran":12,"n_constructed":7,"n_ran_checked":10,"n_instrument":2,"n_unverified":3,"n_samples":15,"n_pointer_only_licence":0,"sample_list":"/paper/efficient-multi-order-gated-aggregation#ran","syntology_url":"https://syntology.ai/paper/2211.03295","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.03295"}}}},{"rank_in_archive_order":56,"model":"PANet","metrics":{"mask AP":"42.0"},"uses_additional_data":false,"paper_date":"2018-03-05","paper":"/paper/path-aggregation-network-for-instance","paper_url":"http://arxiv.org/abs/1803.01534v4","paper_title":"Path Aggregation Network for Instance Segmentation","code":"https://github.com/ultralytics/yolov5","n_code_links":10,"official":{"repos":["ShuLiu1993/PANet"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official","unlocated"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":1,"n_samples":4,"n_pointer_only_licence":2,"sample_list":"/paper/path-aggregation-network-for-instance#ran","syntology_url":"https://syntology.ai/paper/1803.01534","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1803.01534"}}}},{"rank_in_archive_order":57,"model":"CenterMask + VoVNet99","metrics":{"APL":"54.3","APM":"44.4","APS":"24.4","mask AP":"41.8"},"uses_additional_data":false,"paper_date":"2019-11-15","paper":"/paper/centermask-real-time-anchor-free-instance-1","paper_url":"https://arxiv.org/abs/1911.06667v6","paper_title":"CenterMask : Real-Time Anchor-Free Instance Segmentation","code":"https://github.com/youngwanLEE/centermask2","n_code_links":8,"official":{"repos":["youngwanLEE/CenterMask"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2,"sample_list":"/paper/centermask-real-time-anchor-free-instance-1#ran","syntology_url":"https://syntology.ai/paper/1911.06667","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.06667"}}}},{"rank_in_archive_order":58,"model":"SOLOv2(Res-DCN-101-FPN)","metrics":{"AP50":"63.2","AP75":"45.1","APL":"61.6","APM":"45.0","APS":"18.0","mask AP":"41.7"},"uses_additional_data":false,"paper_date":"2020-03-23","paper":"/paper/solov2-dynamic-faster-and-stronger","paper_url":"https://arxiv.org/abs/2003.10152v3","paper_title":"SOLOv2: Dynamic and Fast Instance Segmentation","code":"https://github.com/open-mmlab/mmdetection","n_code_links":18,"official":{"repos":["WXinlong/SOLO"],"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":23,"n_constructed":4,"n_ran_checked":13,"n_instrument":10,"n_unverified":15,"n_samples":38,"n_pointer_only_licence":24,"sample_list":"/paper/solov2-dynamic-faster-and-stronger#ran","syntology_url":"https://syntology.ai/paper/2003.10152","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.10152"}}}},{"rank_in_archive_order":59,"model":"BCNet(ResNeXt-101  + FPN+ FCOS)","metrics":{"mask AP":"41.7"},"uses_additional_data":false,"paper_date":"2021-03-23","paper":"/paper/deep-occlusion-aware-instance-segmentation","paper_url":"https://arxiv.org/abs/2103.12340v1","paper_title":"Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers","code":"https://github.com/lkeab/BCNet","n_code_links":1,"official":{"repos":["lkeab/BCNet"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]},"syntology":{"n_ran":9,"n_constructed":0,"n_ran_checked":4,"n_instrument":5,"n_unverified":3,"n_samples":12,"n_pointer_only_licence":5,"sample_list":"/paper/deep-occlusion-aware-instance-segmentation#ran","syntology_url":"https://syntology.ai/paper/2103.12340","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.12340"}}}},{"rank_in_archive_order":60,"model":"GCNet (ResNeXt-101 + DCN + cascade + GC r16)","metrics":{"mask AP":"41.5%"},"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":61,"model":"DiffusionInst-ResNet101","metrics":{"mask AP":"41.5"},"uses_additional_data":false,"paper_date":"2022-12-06","paper":"/paper/diffusioninst-diffusion-model-for-instance","paper_url":"https://arxiv.org/abs/2212.02773v3","paper_title":"DiffusionInst: Diffusion Model for Instance Segmentation","code":"https://github.com/chenhaoxing/DiffusionInst","n_code_links":2,"official":{"repos":["chenhaoxing/DiffusionInst"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]},"syntology":{"n_ran":12,"n_constructed":0,"n_ran_checked":6,"n_instrument":6,"n_unverified":4,"n_samples":16,"n_pointer_only_licence":7,"sample_list":"/paper/diffusioninst-diffusion-model-for-instance#ran","syntology_url":"https://syntology.ai/paper/2212.02773","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.02773"}}}},{"rank_in_archive_order":62,"model":"BlendMask (ResNet-101 + DCN interval=3)","metrics":{"AP50":"63.1","AP75":"44.6","APL":"54.5","APM":"44.1","APS":"22.7","mask AP":"41.3"},"uses_additional_data":false,"paper_date":"2020-01-02","paper":"/paper/blendmask-top-down-meets-bottom-up-for","paper_url":"https://arxiv.org/abs/2001.00309v3","paper_title":"BlendMask: Top-Down Meets Bottom-Up for Instance Segmentation","code":"https://github.com/aim-uofa/AdelaiDet","n_code_links":9,"official":null,"syntology":null},{"rank_in_archive_order":63,"model":"HTC + ResNeXt-101-FPN + DCN","metrics":{"mask AP":"41.2"},"uses_additional_data":true,"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":64,"model":"HTC + ResNeXt-101-FPN","metrics":{"mask AP":"41.2%"},"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":65,"model":"SOLQ (ResNet101, single scale)","metrics":{"mask AP":"40.9"},"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":66,"model":"VoVNetV1-57","metrics":{"mask AP":"40.8%"},"uses_additional_data":false,"paper_date":"2019-04-22","paper":"/paper/an-energy-and-gpu-computation-efficient","paper_url":"http://arxiv.org/abs/1904.09730v1","paper_title":"An Energy and GPU-Computation Efficient Backbone Network for Real-Time Object Detection","code":"https://github.com/osmr/imgclsmob","n_code_links":12,"official":null,"syntology":null},{"rank_in_archive_order":67,"model":"K-Net-N256 (ResNet-101)","metrics":{"AP50":"63.3","APL":"59","APM":"43.3","APS":"18.8","mask AP":"40.6%"},"uses_additional_data":false,"paper_date":"2021-06-28","paper":"/paper/k-net-towards-unified-image-segmentation","paper_url":"https://arxiv.org/abs/2106.14855v2","paper_title":"K-Net: Towards Unified Image Segmentation","code":"https://github.com/zwwwayne/k-net","n_code_links":1,"official":{"repos":["zwwwayne/k-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":["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/k-net-towards-unified-image-segmentation#ran","syntology_url":"https://syntology.ai/paper/2106.14855","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.14855"}}}},{"rank_in_archive_order":68,"model":"CenterMask + VoVNetV2-99 (single-scale)","metrics":{"AP50":"62.3","AP75":"44.1","APL":"57.0","APM":"42.8","APS":"20.1","mask AP":"40.6"},"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":69,"model":"SOLO(Res-DCN-101-FPN)","metrics":{"AP50":"62.7","AP75":"43.3","APL":"58.9","APM":"43.3","APS":"17.6","mask AP":"40.4"},"uses_additional_data":false,"paper_date":"2019-12-10","paper":"/paper/solo-segmenting-objects-by-locations","paper_url":"https://arxiv.org/abs/1912.04488v3","paper_title":"SOLO: Segmenting Objects by Locations","code":"https://github.com/open-mmlab/mmdetection","n_code_links":24,"official":null,"syntology":null},{"rank_in_archive_order":70,"model":"SOLO (ResNet-DCN-101-FPN)","metrics":{"AP50":"62.7%","AP75":"43.3%","APL":"58.9%","APM":"43.3%","APS":"17.6%","mask AP":"40.4%"},"uses_additional_data":false,"paper_date":"2019-12-10","paper":"/paper/solo-segmenting-objects-by-locations","paper_url":"https://arxiv.org/abs/1912.04488v3","paper_title":"SOLO: Segmenting Objects by Locations","code":"https://github.com/open-mmlab/mmdetection","n_code_links":24,"official":null,"syntology":null},{"rank_in_archive_order":71,"model":"D2Det (ResNet-101, single-scale test)","metrics":{"AP50":"61.5","AP75":"43.7","APL":"54.0","APM":"43.0","APS":"21.7","mask AP":"40.2"},"uses_additional_data":false,"paper_date":"2020-06-01","paper":"/paper/d2det-towards-high-quality-object-detection","paper_url":"http://openaccess.thecvf.com/content_CVPR_2020/html/Cao_D2Det_Towards_High_Quality_Object_Detection_and_Instance_Segmentation_CVPR_2020_paper.html","paper_title":"D2Det: Towards High Quality Object Detection and Instance Segmentation","code":"https://github.com/JialeCao001/D2Det","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":72,"model":"K-Net (ResNet-101)","metrics":{"AP50":"62.8","APL":"58.8","APM":"42.7","APS":"18.7","mask AP":"40.1%"},"uses_additional_data":false,"paper_date":"2021-06-28","paper":"/paper/k-net-towards-unified-image-segmentation","paper_url":"https://arxiv.org/abs/2106.14855v2","paper_title":"K-Net: Towards Unified Image Segmentation","code":"https://github.com/zwwwayne/k-net","n_code_links":1,"official":{"repos":["zwwwayne/k-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":["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/k-net-towards-unified-image-segmentation#ran","syntology_url":"https://syntology.ai/paper/2106.14855","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.14855"}}}},{"rank_in_archive_order":73,"model":"ISTR (ResNet101-FPN-3x, single-scale)","metrics":{"APL":"52.3","APM":"41.9","APS":"22.8","mask AP":"39.9%"},"uses_additional_data":false,"paper_date":"2021-05-03","paper":"/paper/istr-end-to-end-instance-segmentation-with","paper_url":"https://arxiv.org/abs/2105.00637v2","paper_title":"ISTR: End-to-End Instance Segmentation with Transformers","code":"https://github.com/hujiecpp/ISTR","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":74,"model":"BCNet(ResNet-101-FPN + Faster RCNN)","metrics":{"AP50":"61.5","AP75":"43.1","APL":"51.1","APM":"42.4","APS":"22.7","mask AP":"39.8"},"uses_additional_data":false,"paper_date":"2021-03-23","paper":"/paper/deep-occlusion-aware-instance-segmentation","paper_url":"https://arxiv.org/abs/2103.12340v1","paper_title":"Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers","code":"https://github.com/lkeab/BCNet","n_code_links":1,"official":{"repos":["lkeab/BCNet"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]},"syntology":{"n_ran":9,"n_constructed":0,"n_ran_checked":4,"n_instrument":5,"n_unverified":3,"n_samples":12,"n_pointer_only_licence":5,"sample_list":"/paper/deep-occlusion-aware-instance-segmentation#ran","syntology_url":"https://syntology.ai/paper/2103.12340","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.12340"}}}},{"rank_in_archive_order":75,"model":"VoVNetV1-39","metrics":{"mask AP":"39.7%"},"uses_additional_data":false,"paper_date":"2019-04-22","paper":"/paper/an-energy-and-gpu-computation-efficient","paper_url":"http://arxiv.org/abs/1904.09730v1","paper_title":"An Energy and GPU-Computation Efficient Backbone Network for Real-Time Object Detection","code":"https://github.com/osmr/imgclsmob","n_code_links":12,"official":null,"syntology":null},{"rank_in_archive_order":76,"model":"SOLQ (ResNet50, single scale)","metrics":{"mask AP":"39.7"},"uses_additional_data":false,"paper_date":"2021-06-04","paper":"/paper/solq-segmenting-objects-by-learning-queries","paper_url":"https://arxiv.org/abs/2106.02351v3","paper_title":"SOLQ: Segmenting Objects by Learning Queries","code":"https://github.com/megvii-research/SOLQ","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":77,"model":"CenterMask + X101-32x8d (single-scale)","metrics":{"AP50":"61.2","AP75":"42.9","APS":"19.7","mask AP":"39.6"},"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":78,"model":"BCNet(ResNet-101-FPN + FCOS)","metrics":{"AP50":"61.2","AP75":"42.7","APL":"51.0","APM":"42.3","APS":"22.3","mask AP":"39.6"},"uses_additional_data":false,"paper_date":"2021-03-23","paper":"/paper/deep-occlusion-aware-instance-segmentation","paper_url":"https://arxiv.org/abs/2103.12340v1","paper_title":"Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers","code":"https://github.com/lkeab/BCNet","n_code_links":1,"official":{"repos":["lkeab/BCNet"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]},"syntology":{"n_ran":9,"n_constructed":0,"n_ran_checked":4,"n_instrument":5,"n_unverified":3,"n_samples":12,"n_pointer_only_licence":5,"sample_list":"/paper/deep-occlusion-aware-instance-segmentation#ran","syntology_url":"https://syntology.ai/paper/2103.12340","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.12340"}}}},{"rank_in_archive_order":79,"model":"MS R-CNN + ResNet-101 DCN + FPN","metrics":{"mask AP":"39.6%"},"uses_additional_data":false,"paper_date":"2019-03-01","paper":"/paper/mask-scoring-r-cnn","paper_url":"http://arxiv.org/abs/1903.00241v1","paper_title":"Mask Scoring R-CNN","code":"https://github.com/open-mmlab/mmdetection","n_code_links":3,"official":{"repos":["zjhuang22/maskscoring_rcnn"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":2,"sample_list":"/paper/mask-scoring-r-cnn#ran","syntology_url":"https://syntology.ai/paper/1903.00241","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1903.00241"}}}},{"rank_in_archive_order":80,"model":"Cascade R-CNN (ResNet-101-FPN, map-guided)","metrics":{"AP50":"61.4%","AP75":"42.9%","APL":"52.1%","APM":"42.5%","APS":"21.2%","mask AP":"39.5%"},"uses_additional_data":false,"paper_date":"2019-08-21","paper":"/paper/instaboost-boosting-instance-segmentation-via","paper_url":"https://arxiv.org/abs/1908.07801v1","paper_title":"InstaBoost: Boosting Instance Segmentation via Probability Map Guided Copy-Pasting","code":"https://github.com/open-mmlab/mmdetection","n_code_links":3,"official":null,"syntology":null},{"rank_in_archive_order":81,"model":"CPMask","metrics":{"AP50":"60.8","AP75":"42.2","APL":"50.1","APM":"41.8","APS":"22.2","mask AP":"39.2"},"uses_additional_data":false,"paper_date":"2020-07-24","paper":"/paper/commonality-parsing-network-across-shape-and","paper_url":"https://arxiv.org/abs/2007.12387v1","paper_title":"Commonality-Parsing Network across Shape and Appearance for Partially Supervised Instance Segmentation","code":"https://github.com/fanq15/FewX","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":82,"model":"MogaNet-T (Mask R-CNN 1x)","metrics":{"mask AP":"39.1"},"uses_additional_data":false,"paper_date":"2022-11-07","paper":"/paper/efficient-multi-order-gated-aggregation","paper_url":"https://arxiv.org/abs/2211.03295v3","paper_title":"MogaNet: Multi-order Gated Aggregation Network","code":"https://github.com/chengtan9907/OpenSTL","n_code_links":7,"official":{"repos":["Westlake-AI/MogaNet","Westlake-AI/openmixup","chengtan9907/OpenSTL"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":7,"n_ran_no_instrument_failure":10,"n_unverified":3,"ran_from_kinds":["official"]},"syntology":{"n_ran":12,"n_constructed":7,"n_ran_checked":10,"n_instrument":2,"n_unverified":3,"n_samples":15,"n_pointer_only_licence":0,"sample_list":"/paper/efficient-multi-order-gated-aggregation#ran","syntology_url":"https://syntology.ai/paper/2211.03295","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.03295"}}}},{"rank_in_archive_order":83,"model":"PolarMask++ (ResNeXt-101-DCN)","metrics":{"AP50":"64.1","AP75":"40.0","APL":"52.0","APM":"40.2","APS":"22.2","mask AP":"38.7"},"uses_additional_data":true,"paper_date":"2021-05-05","paper":"/paper/polarmask-enhanced-polar-representation-for","paper_url":"https://arxiv.org/abs/2105.02184v1","paper_title":"PolarMask++: Enhanced Polar Representation for Single-Shot Instance Segmentation and Beyond","code":"https://github.com/xieenze/PolarMask","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":84,"model":"ISDA (ours)","metrics":{"AP50":"62","AP75":"41.1","APM":"41.2","APS":"17","mask AP":"38.7"},"uses_additional_data":false,"paper_date":"2022-02-23","paper":"/paper/isda-position-aware-instance-segmentation","paper_url":"https://arxiv.org/abs/2202.12251v1","paper_title":"ISDA: Position-Aware Instance Segmentation with Deformable Attention","code":"https://github.com/yingkaining/isda","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":85,"model":"ISTR (ResNet50-FPN-3x, single-scale)","metrics":{"APL":"50.6","APM":"40.4","APS":"22.1","mask AP":"38.6%"},"uses_additional_data":false,"paper_date":"2021-05-03","paper":"/paper/istr-end-to-end-instance-segmentation-with","paper_url":"https://arxiv.org/abs/2105.00637v2","paper_title":"ISTR: End-to-End Instance Segmentation with Transformers","code":"https://github.com/hujiecpp/ISTR","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":86,"model":"CenterMask + ResNet-101-FPN","metrics":{"mask AP":"38.3"},"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":87,"model":"SipMask (ResNet-101, single-scale test)","metrics":{"AP50":"60.2","AP75":"40.8","APL":"54.3","APM":"40.8","APS":"17.8","mask AP":"38.1"},"uses_additional_data":false,"paper_date":"2020-07-29","paper":"/paper/sipmask-spatial-information-preservation-for","paper_url":"https://arxiv.org/abs/2007.14772v1","paper_title":"SipMask: Spatial Information Preservation for Fast Image and Video Instance Segmentation","code":"https://github.com/JialeCao001/SipMask","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":88,"model":"MaskLab+ (ResNet-101, JFT)","metrics":{"mask AP":"38.1%"},"uses_additional_data":true,"paper_date":"2017-12-13","paper":"/paper/masklab-instance-segmentation-by-refining","paper_url":"http://arxiv.org/abs/1712.04837v1","paper_title":"MaskLab: Instance Segmentation by Refining Object Detection with Semantic and Direction Features","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":89,"model":"EmbedMask (ResNet-101-FPN)","metrics":{"AP50":"59.1%","AP75":"40.3%","APL":"53%","APM":"40.4%","APS":"17.9%","mask AP":"37.7%"},"uses_additional_data":false,"paper_date":"2019-12-04","paper":"/paper/embedmask-embedding-coupling-for-one-stage","paper_url":"https://arxiv.org/abs/1912.01954v2","paper_title":"EmbedMask: Embedding Coupling for One-stage Instance Segmentation","code":"https://github.com/yinghdb/EmbedMask","n_code_links":3,"official":null,"syntology":null},{"rank_in_archive_order":90,"model":"EmbedMask(R-101-FPN)","metrics":{"AP50":"59.1","AP75":"40.3","APM":"40.4","APS":"17.9","mask AP":"37.7"},"uses_additional_data":false,"paper_date":"2019-12-04","paper":"/paper/embedmask-embedding-coupling-for-one-stage","paper_url":"https://arxiv.org/abs/1912.01954v2","paper_title":"EmbedMask: Embedding Coupling for One-stage Instance Segmentation","code":"https://github.com/yinghdb/EmbedMask","n_code_links":3,"official":null,"syntology":null},{"rank_in_archive_order":91,"model":"MogaNet-XT","metrics":{"mask AP":"37.6"},"uses_additional_data":false,"paper_date":"2022-11-07","paper":"/paper/efficient-multi-order-gated-aggregation","paper_url":"https://arxiv.org/abs/2211.03295v3","paper_title":"MogaNet: Multi-order Gated Aggregation Network","code":"https://github.com/chengtan9907/OpenSTL","n_code_links":7,"official":{"repos":["Westlake-AI/MogaNet","Westlake-AI/openmixup","chengtan9907/OpenSTL"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":7,"n_ran_no_instrument_failure":10,"n_unverified":3,"ran_from_kinds":["official"]},"syntology":{"n_ran":12,"n_constructed":7,"n_ran_checked":10,"n_instrument":2,"n_unverified":3,"n_samples":15,"n_pointer_only_licence":0,"sample_list":"/paper/efficient-multi-order-gated-aggregation#ran","syntology_url":"https://syntology.ai/paper/2211.03295","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.03295"}}}},{"rank_in_archive_order":92,"model":"TensorMask (ResNet-101-FPN)","metrics":{"mask AP":"37.3%"},"uses_additional_data":false,"paper_date":"2019-03-28","paper":"/paper/tensormask-a-foundation-for-dense-object","paper_url":"https://arxiv.org/abs/1903.12174v2","paper_title":"TensorMask: A Foundation for Dense Object Segmentation","code":"https://github.com/facebookresearch/detectron2/tree/master/projects/TensorMask","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":93,"model":"Mask R-CNN (ResNeXt-101-FPN)","metrics":{"AP50":"60.0","AP75":"39.4","APL":"53.5","APM":"39.9","APS":"16.9","mask AP":"37.1"},"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":94,"model":"DiffusionInst-ResNet50","metrics":{"mask AP":"37.1"},"uses_additional_data":false,"paper_date":"2022-12-06","paper":"/paper/diffusioninst-diffusion-model-for-instance","paper_url":"https://arxiv.org/abs/2212.02773v3","paper_title":"DiffusionInst: Diffusion Model for Instance Segmentation","code":"https://github.com/chenhaoxing/DiffusionInst","n_code_links":2,"official":{"repos":["chenhaoxing/DiffusionInst"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]},"syntology":{"n_ran":12,"n_constructed":0,"n_ran_checked":6,"n_instrument":6,"n_unverified":4,"n_samples":16,"n_pointer_only_licence":7,"sample_list":"/paper/diffusioninst-diffusion-model-for-instance#ran","syntology_url":"https://syntology.ai/paper/2212.02773","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.02773"}}}},{"rank_in_archive_order":95,"model":"VirTex Mask R-CNN (ResNet-50-FPN)","metrics":{"AP50":"58.4","AP75":"39.7","mask AP":"36.9"},"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":96,"model":"RDSNet (data aug)","metrics":{"AP50":"57.9%","AP75":"39.0%","APL":"51.6%","APM":"39.5%","APS":"16.4%","mask AP":"36.4%"},"uses_additional_data":false,"paper_date":"2019-12-11","paper":"/paper/rdsnet-a-new-deep-architecture-for-reciprocal","paper_url":"https://arxiv.org/abs/1912.05070v1","paper_title":"RDSNet: A New Deep Architecture for Reciprocal Object Detection and Instance Segmentation","code":"https://github.com/wangsr126/RDSNet","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":97,"model":"MogaNet-T","metrics":{"mask AP":"35.8"},"uses_additional_data":false,"paper_date":"2022-11-07","paper":"/paper/efficient-multi-order-gated-aggregation","paper_url":"https://arxiv.org/abs/2211.03295v3","paper_title":"MogaNet: Multi-order Gated Aggregation Network","code":"https://github.com/chengtan9907/OpenSTL","n_code_links":7,"official":{"repos":["Westlake-AI/MogaNet","Westlake-AI/openmixup","chengtan9907/OpenSTL"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":7,"n_ran_no_instrument_failure":10,"n_unverified":3,"ran_from_kinds":["official"]},"syntology":{"n_ran":12,"n_constructed":7,"n_ran_checked":10,"n_instrument":2,"n_unverified":3,"n_samples":15,"n_pointer_only_licence":0,"sample_list":"/paper/efficient-multi-order-gated-aggregation#ran","syntology_url":"https://syntology.ai/paper/2211.03295","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.03295"}}}},{"rank_in_archive_order":98,"model":"A2MIM (ResNet-50 2x)","metrics":{"mask AP":"34.9"},"uses_additional_data":false,"paper_date":"2022-05-27","paper":"/paper/architecture-agnostic-masked-image-modeling","paper_url":"https://arxiv.org/abs/2205.13943v4","paper_title":"Architecture-Agnostic Masked Image Modeling -- From ViT back to CNN","code":"https://github.com/open-mmlab/mmpretrain","n_code_links":3,"official":null,"syntology":null},{"rank_in_archive_order":99,"model":"E2EC DLA-34","metrics":{"AP50":"52.9","AP75":"35.9","mask AP":"33.8"},"uses_additional_data":false,"paper_date":"2022-03-08","paper":"/paper/e2ec-an-end-to-end-contour-based-method-for","paper_url":"https://arxiv.org/abs/2203.04074v1","paper_title":"E2EC: An End-to-End Contour-based Method for High-Quality High-Speed Instance Segmentation","code":"https://github.com/zhang-tao-whu/e2ec","n_code_links":1,"official":{"repos":["zhang-tao-whu/e2ec"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":4,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]},"syntology":{"n_ran":8,"n_constructed":4,"n_ran_checked":5,"n_instrument":3,"n_unverified":2,"n_samples":10,"n_pointer_only_licence":10,"sample_list":"/paper/e2ec-an-end-to-end-contour-based-method-for#ran","syntology_url":"https://syntology.ai/paper/2203.04074","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.04074"}}}},{"rank_in_archive_order":100,"model":"FCIS+++  +OHEM","metrics":{"AP50":"54.5%","mask AP":"33.6%"},"uses_additional_data":false,"paper_date":"2016-11-23","paper":"/paper/fully-convolutional-instance-aware-semantic","paper_url":"http://arxiv.org/abs/1611.07709v2","paper_title":"Fully Convolutional Instance-aware Semantic Segmentation","code":"https://github.com/divamgupta/image-segmentation-keras","n_code_links":3,"official":{"repos":["daijifeng001/TA-FCN"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":3,"n_samples":5,"n_pointer_only_licence":4,"sample_list":"/paper/fully-convolutional-instance-aware-semantic#ran","syntology_url":"https://syntology.ai/paper/1611.07709","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1611.07709"}}}},{"rank_in_archive_order":101,"model":"Mask R-CNN (Bottleneck-injected ResNet-50, FPN)","metrics":{"mask AP":"33.6"},"uses_additional_data":false,"paper_date":"2020-11-25","paper":"/paper/torchdistill-a-modular-configuration-driven","paper_url":"https://arxiv.org/abs/2011.12913v2","paper_title":"torchdistill: A Modular, Configuration-Driven Framework for Knowledge Distillation","code":"https://github.com/yoshitomo-matsubara/torchdistill","n_code_links":1,"official":{"repos":["yoshitomo-matsubara/torchdistill"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":16,"ran_from_kinds":["official"]},"syntology":{"n_ran":10,"n_constructed":0,"n_ran_checked":0,"n_instrument":10,"n_unverified":16,"n_samples":26,"n_pointer_only_licence":0,"sample_list":"/paper/torchdistill-a-modular-configuration-driven#ran","syntology_url":"https://syntology.ai/paper/2011.12913","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2011.12913"}}}},{"rank_in_archive_order":102,"model":"PolarMask (ResNeXt-101-FPN)","metrics":{"AP50":"55.4%","AP75":"33.8%","APL":"46.3%","APM":"35.1%","APS":"15.5%","mask AP":"32.9%"},"uses_additional_data":false,"paper_date":"2019-09-29","paper":"/paper/polarmask-single-shot-instance-segmentation","paper_url":"https://arxiv.org/abs/1909.13226v4","paper_title":"PolarMask: Single Shot Instance Segmentation with Polar Representation","code":"https://github.com/xieenze/PolarMask","n_code_links":2,"official":{"repos":["xieenze/PolarMask"],"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/polarmask-single-shot-instance-segmentation#ran","syntology_url":"https://syntology.ai/paper/1909.13226","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.13226"}}}},{"rank_in_archive_order":103,"model":"PolarMask (ResNet-101-FPN)","metrics":{"AP50":"51.9%","AP75":"31%","APL":"42.8%","APM":"32.4%","APS":"13.4%","mask AP":"30.4%"},"uses_additional_data":false,"paper_date":"2019-09-29","paper":"/paper/polarmask-single-shot-instance-segmentation","paper_url":"https://arxiv.org/abs/1909.13226v4","paper_title":"PolarMask: Single Shot Instance Segmentation with Polar Representation","code":"https://github.com/xieenze/PolarMask","n_code_links":2,"official":{"repos":["xieenze/PolarMask"],"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/polarmask-single-shot-instance-segmentation#ran","syntology_url":"https://syntology.ai/paper/1909.13226","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.13226"}}}},{"rank_in_archive_order":104,"model":"YOLACT (ResNet-50-FPN)","metrics":{"mask AP":"29.8%"},"uses_additional_data":false,"paper_date":"2019-04-04","paper":"/paper/yolact-real-time-instance-segmentation","paper_url":"https://arxiv.org/abs/1904.02689v2","paper_title":"YOLACT: Real-time Instance Segmentation","code":"https://github.com/open-mmlab/mmdetection","n_code_links":48,"official":{"repos":["dbolya/yolact"],"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":18,"n_constructed":0,"n_ran_checked":11,"n_instrument":7,"n_unverified":3,"n_samples":21,"n_pointer_only_licence":9,"sample_list":"/paper/yolact-real-time-instance-segmentation#ran","syntology_url":"https://syntology.ai/paper/1904.02689","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.02689"}}}},{"rank_in_archive_order":105,"model":"FCIS  +OHEM","metrics":{"AP50":"49.5%","APL":"50.0%","APM":"31.3%","APS":"7.1%","mask AP":"29.2%"},"uses_additional_data":false,"paper_date":"2016-11-23","paper":"/paper/fully-convolutional-instance-aware-semantic","paper_url":"http://arxiv.org/abs/1611.07709v2","paper_title":"Fully Convolutional Instance-aware Semantic Segmentation","code":"https://github.com/divamgupta/image-segmentation-keras","n_code_links":3,"official":{"repos":["daijifeng001/TA-FCN"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":3,"n_samples":5,"n_pointer_only_licence":4,"sample_list":"/paper/fully-convolutional-instance-aware-semantic#ran","syntology_url":"https://syntology.ai/paper/1611.07709","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1611.07709"}}}},{"rank_in_archive_order":106,"model":"MultiPath Network","metrics":{"mask AP":"25.0%"},"uses_additional_data":false,"paper_date":"2016-04-07","paper":"/paper/a-multipath-network-for-object-detection","paper_url":"http://arxiv.org/abs/1604.02135v2","paper_title":"A MultiPath Network for Object Detection","code":"https://github.com/facebookresearch/multipathnet","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":107,"model":"InternImage-H","metrics":{"AP50":"80.8","AP75":"62.2","APL":"70.3","APM":"58.9","APS":"41.0"},"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":108,"model":"ResNeSt-200 (multi-scale)","metrics":{"AP50":"70.2","AP75":"51.5","APL":"60.6","APM":"49.6","APS":"30.0"},"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":109,"model":"CenterMask + VoVNetV2-99 (multi-scale)","metrics":{"AP50":"66.2","AP75":"47.4","APS":"27.2"},"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":110,"model":"CenterMask + VoVNetV2-57 (single-scale)","metrics":{"AP50":"60.8","APM":"41.7","APS":"19.4"},"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":111,"model":"MNC","metrics":{"AP50":"44.3%"},"uses_additional_data":false,"paper_date":"2015-12-14","paper":"/paper/instance-aware-semantic-segmentation-via","paper_url":"http://arxiv.org/abs/1512.04412v1","paper_title":"Instance-aware Semantic Segmentation via Multi-task Network Cascades","code":"https://github.com/daijifeng001/MNC","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":112,"model":"ISDA (ResNet-50)","metrics":{"APL":"55.7"},"uses_additional_data":false,"paper_date":"2022-02-23","paper":"/paper/isda-position-aware-instance-segmentation","paper_url":"https://arxiv.org/abs/2202.12251v1","paper_title":"ISDA: Position-Aware Instance Segmentation with Deformable Attention","code":"https://github.com/yingkaining/isda","n_code_links":1,"official":null,"syntology":null}],"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), none had this board among the leaderboards the extractor considered for their tables yet (it keeps at most 10 boards per paper and 4 per dataset; the lists of 1,596 of the 8,888 were already full without this board, so if it was crowded out of them it is not counted), so none await a verdict here.","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":112,"metric_columns":6,"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":1596,"candidates":0,"candidates_capped_note":"candidates = papers that had this board among the leaderboards the extractor considered for their tables; the extractor keeps at most 10 per paper and 4 per dataset, so a board crowded out of a paper's list is not counted and candidates is a floor; papers_read_list_full_without_this_board counts the read papers whose list did not hold this board and had reached 10, or held 4 boards of this board's dataset (the only papers that could have crowded it out); papers_read_at_candidate_cap counts, over every board, the papers whose list reached 10","proposed":0,"no_cell_passed_checks":0,"rejected_by_independent_check":0,"accepted_not_placed":0,"awaiting_verdict":0,"placed":0,"placed_entries_listed":0,"file_lines_unreadable_as_read":0,"since_line":"Since the archive (Syntology): none placed; no newer paper judged to report on this board so far"},"judged_to_report":{"heading":"Newer papers whose tables a model judged to report on this benchmark (a model's judgement, not a result; newest first by arXiv id)","judged_by":{"model":"a model","models_as_recorded":[],"a_record_without_a_model":false,"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here","order":"newest first by arXiv id (the identifier's order, not a rank)","outcomes":{"placed":"placed","no_cell_passed_checks":"no cell passed the extractor's checks","refused_by_rule":"refused by a rule","rejected":"rejected by the independent check","accepted_not_placed":"accepted by the independent check but not placed by this site","awaiting":"awaiting a verdict"},"reason_note":"for refused_by_rule, the rules' plain words for the reason codes the record gives (never the quoted or the actual cell text); null for every other outcome","total":0,"shown_on_page":0,"no_cell_split":{"no_cell_passed_checks_in_ledger":0,"rows_refused_by_rule":0,"rows_no_cell_passed_checks":0},"rows":[]},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per row: of M harvested code samples from that row's paper, n_ran executed on a synthesized fixture (n_ran = n_ran_checked + n_instrument; n_instrument counts failures of Syntology's instrument, not of the code); the other M - n_ran are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"rows_with_graph_line":72,"rows_with_any_sample_ran":70,"rows_with_a_run_with_no_instrument_failure":64,"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":70,"rows_whose_official_repository_has_a_sample_that_ran":47,"rows_whose_official_repository_has_a_run_with_no_instrument_failure":42,"rows_community_repositories_only":14,"rows_runs_from_other_or_unrecorded_repositories":0,"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":36,"distinct_papers_with_any_sample_ran":35,"distinct_papers_with_a_run_with_no_instrument_failure":29,"samples_over_distinct_papers":{"n_ran":454,"n_constructed":63,"n_ran_checked":289,"n_instrument":165,"n_unverified":229,"n_samples":683,"n_pointer_only_licence":203,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":867,"n_constructed":171,"n_ran_checked":572,"n_instrument":295,"n_unverified":397,"n_samples":1264,"n_pointer_only_licence":345,"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":"973b370a9cc73ad741b530c23df50df00e7338a1c42289722a13fe888c729d1c","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}