{"url":"/task/instance-segmentation","name":"Instance Segmentation","slug":"instance-segmentation","description_markdown":"**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)","categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":2262,"papers_with_code":1158,"benchmarks":36,"benchmark_tables_in_archive":36,"benchmark_tables_shown":36,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":111,"subtasks":17,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/instance-segmentation-on-coco","slug":"instance-segmentation-on-coco","dataset":"COCO test-dev","dataset_url":"/dataset/coco","rows_in_archive":112,"metrics":["mask AP","AP50","AP75","APS","APM","APL"],"first_row_in_archive_order":{"model":"Co-DETR","paper_title":"DETRs with Collaborative Hybrid Assignments Training","paper_url":"/paper/detrs-with-collaborative-hybrid-assignments","paper_date":"2022-11-22","arxiv_id":"2211.12860","code_links":[{"title":"open-mmlab/mmdetection","url":"https://github.com/open-mmlab/mmdetection"},{"title":"siyuanliii/masa","url":"https://github.com/siyuanliii/masa"},{"title":"sense-x/co-detr","url":"https://github.com/sense-x/co-detr"},{"title":"anenbergb/Co-DETR-TensorRT","url":"https://github.com/anenbergb/Co-DETR-TensorRT"},{"title":"MindCode-4/code-3","url":"https://github.com/MindCode-4/code-3/tree/main/detr"},{"title":"code-implementation1/Code1","url":"https://github.com/code-implementation1/Code1/tree/main/detr"}],"syntology":{"n":5,"n_ran":0,"n_unverified":5,"n_pointer_only":0}}},{"leaderboard":"/sota/instance-segmentation-on-coco-minival","slug":"instance-segmentation-on-coco-minival","dataset":"COCO minival","dataset_url":"/dataset/coco","rows_in_archive":93,"metrics":["mask AP","AP50","AP75","APL","APM","APS","GFLOPs","Params (M)","box AP"],"first_row_in_archive_order":{"model":"Co-DETR","paper_title":"DETRs with Collaborative Hybrid Assignments Training","paper_url":"/paper/detrs-with-collaborative-hybrid-assignments","paper_date":"2022-11-22","arxiv_id":"2211.12860","code_links":[{"title":"open-mmlab/mmdetection","url":"https://github.com/open-mmlab/mmdetection"},{"title":"siyuanliii/masa","url":"https://github.com/siyuanliii/masa"},{"title":"sense-x/co-detr","url":"https://github.com/sense-x/co-detr"},{"title":"anenbergb/Co-DETR-TensorRT","url":"https://github.com/anenbergb/Co-DETR-TensorRT"},{"title":"MindCode-4/code-3","url":"https://github.com/MindCode-4/code-3/tree/main/detr"},{"title":"code-implementation1/Code1","url":"https://github.com/code-implementation1/Code1/tree/main/detr"}],"syntology":{"n":5,"n_ran":0,"n_unverified":5,"n_pointer_only":0}}},{"leaderboard":"/sota/instance-segmentation-on-lvis-v1-0-val","slug":"instance-segmentation-on-lvis-v1-0-val","dataset":"LVIS v1.0 val","dataset_url":"/dataset/lvis","rows_in_archive":25,"metrics":["mask AP","mask APr"],"first_row_in_archive_order":{"model":"Co-DETR (single-scale)","paper_title":"DETRs with Collaborative Hybrid Assignments Training","paper_url":"/paper/detrs-with-collaborative-hybrid-assignments","paper_date":"2022-11-22","arxiv_id":"2211.12860","code_links":[{"title":"open-mmlab/mmdetection","url":"https://github.com/open-mmlab/mmdetection"},{"title":"siyuanliii/masa","url":"https://github.com/siyuanliii/masa"},{"title":"sense-x/co-detr","url":"https://github.com/sense-x/co-detr"},{"title":"anenbergb/Co-DETR-TensorRT","url":"https://github.com/anenbergb/Co-DETR-TensorRT"},{"title":"MindCode-4/code-3","url":"https://github.com/MindCode-4/code-3/tree/main/detr"},{"title":"code-implementation1/Code1","url":"https://github.com/code-implementation1/Code1/tree/main/detr"}],"syntology":{"n":5,"n_ran":0,"n_unverified":5,"n_pointer_only":0}}},{"leaderboard":"/sota/instance-segmentation-on-cityscapes-val","slug":"instance-segmentation-on-cityscapes-val","dataset":"Cityscapes val","dataset_url":"/dataset/cityscapes","rows_in_archive":17,"metrics":["mask AP","AP50","AP"],"first_row_in_archive_order":{"model":"ViT-P (OneFormer, ConvNeXt-L, single-scale, 512x1024, Mapillary Vistas-pretrained)","paper_title":"The Missing Point in Vision Transformers for Universal Image Segmentation","paper_url":"/paper/the-missing-point-in-vision-transformers-for","paper_date":"2025-05-26","arxiv_id":"2505.19795","code_links":[{"title":"sajjad-sh33/vit-p","url":"https://github.com/sajjad-sh33/vit-p"}],"syntology":null}},{"leaderboard":"/sota/instance-segmentation-on-ade20k-val","slug":"instance-segmentation-on-ade20k-val","dataset":"ADE20K val","dataset_url":"/dataset/ade20k","rows_in_archive":14,"metrics":["AP","APL","APM","APS"],"first_row_in_archive_order":{"model":"OneFormer (InternImage-H, emb_dim=1024, single-scale, 896x896, COCO-Pretrained)","paper_title":"OneFormer: One Transformer to Rule Universal Image Segmentation","paper_url":"/paper/oneformer-one-transformer-to-rule-universal","paper_date":"2022-11-10","arxiv_id":"2211.06220","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"SHI-Labs/OneFormer","url":"https://github.com/SHI-Labs/OneFormer"},{"title":"yangyucheng000/University","url":"https://github.com/yangyucheng000/University/tree/main/model-1/oneformer"},{"title":"MindCode-4/code-2","url":"https://github.com/MindCode-4/code-2/tree/main/oneformer"}],"syntology":{"n":5,"n_ran":0,"n_unverified":5,"n_pointer_only":0}}},{"leaderboard":"/sota/instance-segmentation-on-cityscapes","slug":"instance-segmentation-on-cityscapes","dataset":"Cityscapes test","dataset_url":"/dataset/cityscapes","rows_in_archive":11,"metrics":["mask AP"],"first_row_in_archive_order":{"model":"Deep Watershed Transform","paper_title":"Deep Watershed Transform for Instance Segmentation","paper_url":"/paper/deep-watershed-transform-for-instance","paper_date":"2016-11-24","arxiv_id":"1611.08303","code_links":[{"title":"min2209/dwt","url":"https://github.com/min2209/dwt"},{"title":"timothyn617/watershed-transform","url":"https://github.com/timothyn617/watershed-transform"}],"syntology":{"n":8,"n_ran":0,"n_unverified":8,"n_pointer_only":0}}},{"leaderboard":"/sota/instance-segmentation-on-armbench","slug":"instance-segmentation-on-armbench","dataset":"ARMBench","dataset_url":"/dataset/armbench","rows_in_archive":7,"metrics":["AP50","AP75"],"first_row_in_archive_order":{"model":"RISE (VIT-B)","paper_title":"Robot Instance Segmentation with Few Annotations for Grasping","paper_url":"/paper/robot-instance-segmentation-with-few","paper_date":"2024-07-01","arxiv_id":"2407.01302","code_links":[{"title":"mkimhi/RISE","url":"https://github.com/mkimhi/RISE"}],"syntology":null}},{"leaderboard":"/sota/instance-segmentation-on-occluded-coco","slug":"instance-segmentation-on-occluded-coco","dataset":"Occluded COCO","dataset_url":"/dataset/occluded-coco","rows_in_archive":6,"metrics":["Mean Recall"],"first_row_in_archive_order":{"model":"Swin-B + Cascade Mask R-CNN (tri-layer modelling)","paper_title":"A Tri-Layer Plugin to Improve Occluded Detection","paper_url":"/paper/a-tri-layer-plugin-to-improve-occluded","paper_date":"2022-10-18","arxiv_id":"2210.10046","code_links":[{"title":"Championchess/Tri-Layer_Plugin_Occluded_Detection","url":"https://github.com/Championchess/Tri-Layer_Plugin_Occluded_Detection"}],"syntology":null}},{"leaderboard":"/sota/instance-segmentation-on-separated-coco","slug":"instance-segmentation-on-separated-coco","dataset":"Separated COCO","dataset_url":"/dataset/separated-coco","rows_in_archive":6,"metrics":["Mean Recall"],"first_row_in_archive_order":{"model":"Swin-B + Cascade Mask R-CNN (tri-layer modelling)","paper_title":"A Tri-Layer Plugin to Improve Occluded Detection","paper_url":"/paper/a-tri-layer-plugin-to-improve-occluded","paper_date":"2022-10-18","arxiv_id":"2210.10046","code_links":[{"title":"Championchess/Tri-Layer_Plugin_Occluded_Detection","url":"https://github.com/Championchess/Tri-Layer_Plugin_Occluded_Detection"}],"syntology":null}},{"leaderboard":"/sota/instance-segmentation-on-isaid","slug":"instance-segmentation-on-isaid","dataset":"iSAID","dataset_url":"/dataset/isaid","rows_in_archive":5,"metrics":["Average Precision"],"first_row_in_archive_order":{"model":"PANet++","paper_title":"iSAID: A Large-scale Dataset for Instance Segmentation in Aerial Images","paper_url":"/paper/isaid-a-large-scale-dataset-for-instance","paper_date":"2019-05-30","arxiv_id":"1905.12886","code_links":[{"title":"CAPTAIN-WHU/iSAID_Devkit","url":"https://github.com/CAPTAIN-WHU/iSAID_Devkit"},{"title":"yeliudev/catnet","url":"https://github.com/yeliudev/catnet"},{"title":"Anirudh0707/Roads-and-Building-Segmentation","url":"https://github.com/Anirudh0707/Roads-and-Building-Segmentation"}],"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}}},{"leaderboard":"/sota/instance-segmentation-on-tbbr","slug":"instance-segmentation-on-tbbr","dataset":"TBBR","dataset_url":"/dataset/tbbr","rows_in_archive":5,"metrics":["Average Recall@IoU:0.5-0.95"],"first_row_in_archive_order":{"model":"Swin-T (ImageNet-1k pretrain)","paper_title":"Deep learning approaches to building rooftop thermal bridge detection from aerial images","paper_url":"/paper/deep-learning-approaches-to-building-rooftop","paper_date":"2022-12-12","arxiv_id":null,"code_links":[{"title":"Helmholtz-AI-Energy/TBBRDet","url":"https://github.com/Helmholtz-AI-Energy/TBBRDet"}],"syntology":null}},{"leaderboard":"/sota/instance-segmentation-on-bdd100k-val","slug":"instance-segmentation-on-bdd100k-val","dataset":"BDD100K val","dataset_url":"/dataset/bdd100k","rows_in_archive":4,"metrics":["AP"],"first_row_in_archive_order":{"model":"Mask Transfiner","paper_title":"Mask Transfiner for High-Quality Instance Segmentation","paper_url":"/paper/mask-transfiner-for-high-quality-instance","paper_date":"2021-11-26","arxiv_id":"2111.13673","code_links":[{"title":"SysCV/transfiner","url":"https://github.com/SysCV/transfiner"}],"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}}},{"leaderboard":"/sota/instance-segmentation-on-coco-2017-val","slug":"instance-segmentation-on-coco-2017-val","dataset":"COCO 2017 val","dataset_url":null,"rows_in_archive":4,"metrics":["mask AP*","mask AP","AP"],"first_row_in_archive_order":{"model":"SparK (ConvNeXt V1-B Mask R-CNN)","paper_title":"Designing BERT for Convolutional Networks: Sparse and Hierarchical Masked Modeling","paper_url":"/paper/designing-bert-for-convolutional-networks","paper_date":"2023-01-09","arxiv_id":"2301.03580","code_links":[{"title":"keyu-tian/spark","url":"https://github.com/keyu-tian/spark"},{"title":"Factral/UnMix-NeRF","url":"https://github.com/Factral/UnMix-NeRF"}],"syntology":{"n":14,"n_ran":5,"n_unverified":9,"n_pointer_only":0}}},{"leaderboard":"/sota/instance-segmentation-on-coco-val-panoptic","slug":"instance-segmentation-on-coco-val-panoptic","dataset":"COCO val (panoptic labels)","dataset_url":null,"rows_in_archive":4,"metrics":["AP"],"first_row_in_archive_order":{"model":"OneFormer (InternImage-H, emb_dim=1024, single-scale)","paper_title":"OneFormer: One Transformer to Rule Universal Image Segmentation","paper_url":"/paper/oneformer-one-transformer-to-rule-universal","paper_date":"2022-11-10","arxiv_id":"2211.06220","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"SHI-Labs/OneFormer","url":"https://github.com/SHI-Labs/OneFormer"},{"title":"yangyucheng000/University","url":"https://github.com/yangyucheng000/University/tree/main/model-1/oneformer"},{"title":"MindCode-4/code-2","url":"https://github.com/MindCode-4/code-2/tree/main/oneformer"}],"syntology":{"n":5,"n_ran":0,"n_unverified":5,"n_pointer_only":0}}},{"leaderboard":"/sota/instance-segmentation-on-oodis","slug":"instance-segmentation-on-oodis","dataset":"OoDIS","dataset_url":"/dataset/oodis","rows_in_archive":3,"metrics":["AP","AP50"],"first_row_in_archive_order":{"model":"UGainS","paper_title":"UGainS: Uncertainty Guided Anomaly Instance Segmentation","paper_url":"/paper/ugains-uncertainty-guided-anomaly-instance","paper_date":"2023-08-03","arxiv_id":"2308.02046","code_links":[{"title":"kumuji/ugains","url":"https://github.com/kumuji/ugains"}],"syntology":null}},{"leaderboard":"/sota/instance-segmentation-on-nyudv2-is","slug":"instance-segmentation-on-nyudv2-is","dataset":"NYUDv2-IS","dataset_url":"/dataset/nyudv2-is","rows_in_archive":2,"metrics":["mask AP"],"first_row_in_archive_order":{"model":"IAM + SOLQ","paper_title":"IAM: Enhancing RGB-D Instance Segmentation with New Benchmarks","paper_url":"/paper/iam-enhancing-rgb-d-instance-segmentation","paper_date":"2025-01-03","arxiv_id":"2501.01685","code_links":[{"title":"aim-skku/sun-rgbd-is","url":"https://github.com/aim-skku/sun-rgbd-is"},{"title":"aim-skku/nyudv2-is","url":"https://github.com/aim-skku/nyudv2-is"},{"title":"aim-skku/box-is","url":"https://github.com/aim-skku/box-is"}],"syntology":null}},{"leaderboard":"/sota/instance-segmentation-on-sun-rgbd-is","slug":"instance-segmentation-on-sun-rgbd-is","dataset":"SUN-RGBD-IS","dataset_url":"/dataset/sun-rgbd-is","rows_in_archive":2,"metrics":["mask AP"],"first_row_in_archive_order":{"model":"IAM + SOLQ","paper_title":"IAM: Enhancing RGB-D Instance Segmentation with New Benchmarks","paper_url":"/paper/iam-enhancing-rgb-d-instance-segmentation","paper_date":"2025-01-03","arxiv_id":"2501.01685","code_links":[{"title":"aim-skku/sun-rgbd-is","url":"https://github.com/aim-skku/sun-rgbd-is"},{"title":"aim-skku/nyudv2-is","url":"https://github.com/aim-skku/nyudv2-is"},{"title":"aim-skku/box-is","url":"https://github.com/aim-skku/box-is"}],"syntology":null}},{"leaderboard":"/sota/instance-segmentation-on-uiis","slug":"instance-segmentation-on-uiis","dataset":"UIIS","dataset_url":"/dataset/uiis-dataset","rows_in_archive":2,"metrics":["mAP","Prams（M）"],"first_row_in_archive_order":{"model":"WaterMask RCNN","paper_title":"WaterMask: Instance Segmentation for Underwater Imagery","paper_url":"/paper/watermask-instance-segmentation-for","paper_date":"2023-01-01","arxiv_id":null,"code_links":[{"title":"liamlian0727/watermask","url":"https://github.com/liamlian0727/watermask"}],"syntology":null}},{"leaderboard":"/sota/instance-segmentation-on-box-is","slug":"instance-segmentation-on-box-is","dataset":"Box-IS","dataset_url":"/dataset/box-is","rows_in_archive":1,"metrics":["mask AP"],"first_row_in_archive_order":{"model":"IAM + SOLQ","paper_title":"IAM: Enhancing RGB-D Instance Segmentation with New Benchmarks","paper_url":"/paper/iam-enhancing-rgb-d-instance-segmentation","paper_date":"2025-01-03","arxiv_id":"2501.01685","code_links":[{"title":"aim-skku/sun-rgbd-is","url":"https://github.com/aim-skku/sun-rgbd-is"},{"title":"aim-skku/nyudv2-is","url":"https://github.com/aim-skku/nyudv2-is"},{"title":"aim-skku/box-is","url":"https://github.com/aim-skku/box-is"}],"syntology":null}},{"leaderboard":"/sota/instance-segmentation-on-cityscapes-1","slug":"instance-segmentation-on-cityscapes-1","dataset":"Cityscapes","dataset_url":"/dataset/cityscapes","rows_in_archive":1,"metrics":["AP"],"first_row_in_archive_order":{"model":"CAST","paper_title":"CAST: Contrastive Adaptation and Distillation for Semi-Supervised Instance Segmentation","paper_url":"/paper/cast-contrastive-adaptation-and-distillation","paper_date":"2025-05-28","arxiv_id":"2505.21904","code_links":[],"syntology":null}},{"leaderboard":"/sota/instance-segmentation-on-coco-3","slug":"instance-segmentation-on-coco-3","dataset":"COCO","dataset_url":null,"rows_in_archive":1,"metrics":["maskAP","maskAP50","maskAP75"],"first_row_in_archive_order":{"model":"ColorMAE-Green-ViTB-1600","paper_title":"ColorMAE: Exploring data-independent masking strategies in Masked AutoEncoders","paper_url":"/paper/colormae-exploring-data-independent-masking","paper_date":"2024-07-17","arxiv_id":"2407.13036","code_links":[{"title":"carlosh93/ColorMAE","url":"https://github.com/carlosh93/ColorMAE"}],"syntology":null}},{"leaderboard":"/sota/instance-segmentation-on-coco-minval","slug":"instance-segmentation-on-coco-minval","dataset":"coco minval","dataset_url":"/dataset/coco","rows_in_archive":1,"metrics":["APL"],"first_row_in_archive_order":{"model":"R3-CNN (ResNet-50-FPN, GC-Net)","paper_title":"Recursively Refined R-CNN: Instance Segmentation with Self-RoI Rebalancing","paper_url":"/paper/recursively-refined-r-cnn-instance","paper_date":"2021-04-03","arxiv_id":"2104.01329","code_links":[{"title":"IMPLabUniPr/mmdetection","url":"https://github.com/IMPLabUniPr/mmdetection"}],"syntology":null}},{"leaderboard":"/sota/instance-segmentation-on-coco-n-medium","slug":"instance-segmentation-on-coco-n-medium","dataset":"COCO-N Medium","dataset_url":"/dataset/coco-n-medium","rows_in_archive":1,"metrics":["mIOU"],"first_row_in_archive_order":{"model":"Mask R-CNN ResNet-50 FPN","paper_title":"Benchmarking Label Noise in Instance Segmentation: Spatial Noise Matters","paper_url":"/paper/benchmarking-label-noise-in-instance","paper_date":"2024-06-16","arxiv_id":"2406.10891","code_links":[{"title":"eden500/Noisy-Labels-Instance-Segmentation","url":"https://github.com/eden500/Noisy-Labels-Instance-Segmentation"}],"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":0}}},{"leaderboard":"/sota/instance-segmentation-on-coco-val2017","slug":"instance-segmentation-on-coco-val2017","dataset":"COCO val2017","dataset_url":null,"rows_in_archive":1,"metrics":["AP50","AP75"],"first_row_in_archive_order":{"model":"MogaNet-S (256x192)","paper_title":"MogaNet: Multi-order Gated Aggregation Network","paper_url":"/paper/efficient-multi-order-gated-aggregation","paper_date":"2022-11-07","arxiv_id":"2211.03295","code_links":[{"title":"chengtan9907/OpenSTL","url":"https://github.com/chengtan9907/OpenSTL"},{"title":"chengtan9907/simvpv2","url":"https://github.com/chengtan9907/simvpv2"},{"title":"Westlake-AI/openmixup","url":"https://github.com/Westlake-AI/openmixup"},{"title":"leondgarse/keras_cv_attention_models","url":"https://github.com/leondgarse/keras_cv_attention_models/tree/main/keras_cv_attention_models/moganet"},{"title":"shanglianlm0525/CvPytorch","url":"https://github.com/shanglianlm0525/CvPytorch"},{"title":"Westlake-AI/MogaNet","url":"https://github.com/Westlake-AI/MogaNet"},{"title":"birder/birder","url":"https://gitlab.com/birder/birder"}],"syntology":{"n":15,"n_ran":12,"n_unverified":3,"n_pointer_only":0}}},{"leaderboard":"/sota/instance-segmentation-on-ishape","slug":"instance-segmentation-on-ishape","dataset":"iShape","dataset_url":"/dataset/ishape","rows_in_archive":1,"metrics":["mask AP"],"first_row_in_archive_order":{"model":"ASIS(baseline)","paper_title":"iShape: A First Step Towards Irregular Shape Instance Segmentation","paper_url":"/paper/ishape-a-first-step-towards-irregular-shape","paper_date":"2021-09-30","arxiv_id":"2109.15068","code_links":[],"syntology":null}},{"leaderboard":"/sota/instance-segmentation-on-kins","slug":"instance-segmentation-on-kins","dataset":"KINS","dataset_url":"/dataset/kins","rows_in_archive":1,"metrics":["mAP"],"first_row_in_archive_order":{"model":"BCNet","paper_title":"Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers","paper_url":"/paper/deep-occlusion-aware-instance-segmentation","paper_date":"2021-03-23","arxiv_id":"2103.12340","code_links":[{"title":"lkeab/BCNet","url":"https://github.com/lkeab/BCNet"}],"syntology":{"n":12,"n_ran":7,"n_unverified":5,"n_pointer_only":0}}},{"leaderboard":"/sota/instance-segmentation-on-ldd","slug":"instance-segmentation-on-ldd","dataset":"LDD","dataset_url":"/dataset/ldd","rows_in_archive":1,"metrics":["mask AP"],"first_row_in_archive_order":{"model":"R^3-CNN","paper_title":"LDD: A Dataset for Grape Diseases Object Detection and Instance Segmentation","paper_url":"/paper/ldd-a-dataset-for-grape-diseases-object","paper_date":"2022-06-21","arxiv_id":"2206.10192","code_links":[],"syntology":null}},{"leaderboard":"/sota/instance-segmentation-on-leaf-segmentation","slug":"instance-segmentation-on-leaf-segmentation","dataset":"Leaf Segmentation Challenge","dataset_url":null,"rows_in_archive":1,"metrics":["Dice Scoe"],"first_row_in_archive_order":{"model":"LeafMask","paper_title":"LeafMask: Towards Greater Accuracy on Leaf Segmentation","paper_url":"/paper/leafmask-towards-greater-accuracy-on-leaf","paper_date":"2021-08-08","arxiv_id":"2108.03568","code_links":[{"title":"easton-cau/LeafMask","url":"https://github.com/easton-cau/LeafMask"}],"syntology":null}},{"leaderboard":"/sota/instance-segmentation-on-lvis-v1-0-test-dev","slug":"instance-segmentation-on-lvis-v1-0-test-dev","dataset":"LVIS v1.0 test-dev","dataset_url":"/dataset/lvis","rows_in_archive":1,"metrics":["mask AP"],"first_row_in_archive_order":{"model":"R50-FPN-MaskRCNN-TTA","paper_title":"1st Place Solution of LVIS Challenge 2020: A Good Box is not a Guarantee of a Good Mask","paper_url":"/paper/1st-place-solution-of-lvis-challenge-2020-a","paper_date":"2020-09-03","arxiv_id":"2009.01559","code_links":[],"syntology":null}},{"leaderboard":"/sota/instance-segmentation-on-nuscenes","slug":"instance-segmentation-on-nuscenes","dataset":"nuScenes","dataset_url":"/dataset/nuscenes","rows_in_archive":1,"metrics":["MOTA"],"first_row_in_archive_order":{"model":"TraDeS","paper_title":"Track to Detect and Segment: An Online Multi-Object Tracker","paper_url":"/paper/track-to-detect-and-segment-an-online-multi","paper_date":"2021-03-16","arxiv_id":"2103.08808","code_links":[{"title":"JialianW/TraDeS","url":"https://github.com/JialianW/TraDeS"}],"syntology":{"n":4,"n_ran":4,"n_unverified":0,"n_pointer_only":0}}},{"leaderboard":"/sota/instance-segmentation-on-nyu-depth-v2","slug":"instance-segmentation-on-nyu-depth-v2","dataset":"NYU Depth v2","dataset_url":"/dataset/nyuv2","rows_in_archive":1,"metrics":["mAP@0.5"],"first_row_in_archive_order":{"model":"SGPN-CNN","paper_title":"SGPN: Similarity Group Proposal Network for 3D Point Cloud Instance Segmentation","paper_url":"/paper/sgpn-similarity-group-proposal-network-for-3d","paper_date":"2017-11-23","arxiv_id":"1711.08588","code_links":[{"title":"laughtervv/SGPN","url":"https://github.com/laughtervv/SGPN"}],"syntology":null}},{"leaderboard":"/sota/instance-segmentation-on-partnet","slug":"instance-segmentation-on-partnet","dataset":"PartNet","dataset_url":"/dataset/partnet","rows_in_archive":1,"metrics":["mAP50"],"first_row_in_archive_order":{"model":"PE","paper_title":"Point Cloud Instance Segmentation using Probabilistic Embeddings","paper_url":"/paper/point-cloud-instance-segmentation-using","paper_date":"2019-11-30","arxiv_id":"1912.00145","code_links":[],"syntology":null}},{"leaderboard":"/sota/instance-segmentation-on-texbig-2022-test","slug":"instance-segmentation-on-texbig-2022-test","dataset":"TexBiG 2022 test","dataset_url":"/dataset/texbig","rows_in_archive":1,"metrics":["mAP@0.5:0.95:0.05"],"first_row_in_archive_order":{"model":"VSR (Vison, Semantics and Relation Model)","paper_title":"A Dataset for Analysing Complex Document Layouts in the Digital Humanities and Its Evaluation with Krippendorff’s Alpha","paper_url":"/paper/a-dataset-for-analysing-complex-document","paper_date":"2022-09-20","arxiv_id":null,"code_links":[{"title":"Madave94/kalphacv","url":"https://github.com/Madave94/kalphacv"},{"title":"Madave94/VSR-TexBiG-Dataset","url":"https://github.com/Madave94/VSR-TexBiG-Dataset"}],"syntology":null}},{"leaderboard":"/sota/instance-segmentation-on-texbig-2023-test","slug":"instance-segmentation-on-texbig-2023-test","dataset":"TexBiG 2023 test","dataset_url":"/dataset/texbig","rows_in_archive":1,"metrics":["mAP@0.5:0.95:0.05"],"first_row_in_archive_order":{"model":"DetectoRS + LAEM","paper_title":"Drawing the Same Bounding Box Twice? Coping Noisy Annotations in Object Detection with Repeated Labels","paper_url":"/paper/drawing-the-same-bounding-box-twice-coping","paper_date":"2023-09-18","arxiv_id":"2309.09742","code_links":[{"title":"madave94/gtiod","url":"https://github.com/madave94/gtiod"}],"syntology":null}},{"leaderboard":"/sota/instance-segmentation-on-uavbillboards","slug":"instance-segmentation-on-uavbillboards","dataset":"UAVBillboards","dataset_url":"/dataset/uav-billboards","rows_in_archive":1,"metrics":["mask AP"],"first_row_in_archive_order":{"model":"YOLOv8-X","paper_title":"Mapping urban large-area advertising structures using drone imagery and deep learning-based spatial data analysis","paper_url":"/paper/mapping-urban-large-area-advertising","paper_date":"2024-07-09","arxiv_id":null,"code_links":[{"title":"PUTvision/UAVBillboards","url":"https://github.com/PUTvision/UAVBillboards"}],"syntology":null}},{"leaderboard":"/sota/instance-segmentation-on-ufba-425","slug":"instance-segmentation-on-ufba-425","dataset":"UFBA-425","dataset_url":"/dataset/ufba-425","rows_in_archive":1,"metrics":["Dice Coef"],"first_row_in_archive_order":{"model":"BB-UNet","paper_title":"Instance Segmentation and Teeth Classification in Panoramic X-rays","paper_url":"/paper/instance-segmentation-and-teeth","paper_date":"2024-06-06","arxiv_id":"2406.03747","code_links":[{"title":"devichand579/Instance_seg_teeth","url":"https://github.com/devichand579/Instance_seg_teeth"}],"syntology":null}}],"datasets":[{"url":"/dataset/coco","name":"COCO (Common Objects in Context)","full_name":"Common Objects in Context","num_papers_in_archive":11922},{"url":"/dataset/cityscapes","name":"Cityscapes","full_name":"","num_papers_in_archive":3702},{"url":"/dataset/nuscenes","name":"nuScenes","full_name":"","num_papers_in_archive":2139},{"url":"/dataset/ade20k","name":"ADE20K","full_name":"","num_papers_in_archive":1213},{"url":"/dataset/nyuv2","name":"NYUv2","full_name":"NYU-Depth V2","num_papers_in_archive":986},{"url":"/dataset/lvis","name":"LVIS","full_name":"","num_papers_in_archive":551},{"url":"/dataset/bdd100k","name":"BDD100K","full_name":"","num_papers_in_archive":469},{"url":"/dataset/kitti-360","name":"KITTI-360","full_name":"","num_papers_in_archive":246},{"url":"/dataset/youtubevis","name":"YouTube-VIS 2019","full_name":"","num_papers_in_archive":163},{"url":"/dataset/objects365","name":"Objects365","full_name":"","num_papers_in_archive":161},{"url":"/dataset/partnet","name":"PartNet","full_name":"","num_papers_in_archive":156},{"url":"/dataset/hypersim","name":"Hypersim","full_name":"","num_papers_in_archive":108},{"url":"/dataset/isaid","name":"iSAID","full_name":"","num_papers_in_archive":81},{"url":"/dataset/3d-future","name":"3D-FUTURE","full_name":"","num_papers_in_archive":48},{"url":"/dataset/wilddash","name":"WildDash","full_name":"","num_papers_in_archive":47},{"url":"/dataset/synscapes","name":"Synscapes","full_name":"","num_papers_in_archive":46},{"url":"/dataset/sixray","name":"SIXray","full_name":null,"num_papers_in_archive":39},{"url":"/dataset/stpls3d","name":"STPLS3D","full_name":"","num_papers_in_archive":36},{"url":"/dataset/ocid","name":"OCID","full_name":"Object Clutter Indoor Dataset","num_papers_in_archive":29},{"url":"/dataset/uvo","name":"UVO","full_name":"Unidentified Video Objects: A Benchmark for Dense, Open-World Segmentation","num_papers_in_archive":27},{"url":"/dataset/scribblesup","name":"ScribbleSup","full_name":"PASCAL-Scribble Dataset","num_papers_in_archive":26},{"url":"/dataset/satlas","name":"Satlas","full_name":"","num_papers_in_archive":22},{"url":"/dataset/hi4d","name":"Hi4D","full_name":"","num_papers_in_archive":19},{"url":"/dataset/livecell","name":"LIVECell","full_name":"Label-free In Vitro image Examples of Cells","num_papers_in_archive":18},{"url":"/dataset/cryonuseg","name":"CryoNuSeg","full_name":"","num_papers_in_archive":16},{"url":"/dataset/grit","name":"GRIT","full_name":"General Robust Image Task Benchmark","num_papers_in_archive":16},{"url":"/dataset/fashionpedia","name":"Fashionpedia","full_name":"","num_papers_in_archive":14},{"url":"/dataset/ttpla","name":"TTPLA","full_name":"Transmission Towers and Power Lines (TTPLA)","num_papers_in_archive":13},{"url":"/dataset/waterscenes","name":"WaterScenes","full_name":"","num_papers_in_archive":13},{"url":"/dataset/trashcan","name":"TrashCan","full_name":"","num_papers_in_archive":12},{"url":"/dataset/taco","name":"TACO","full_name":null,"num_papers_in_archive":11},{"url":"/dataset/cropandweed-dataset","name":"CropAndWeed","full_name":"","num_papers_in_archive":10},{"url":"/dataset/spacenet-2","name":"SpaceNet 2","full_name":"SpaceNet 2: Building Detection v2","num_papers_in_archive":10},{"url":"/dataset/airs","name":"AIRS","full_name":"","num_papers_in_archive":9},{"url":"/dataset/phenobench","name":"PhenoBench","full_name":"PhenoBench — A Large Dataset and Benchmarks for Semantic Image Interpretation in the Agricultural Domain","num_papers_in_archive":9},{"url":"/dataset/uiis-dataset","name":"UIIS","full_name":"General Underwater Image Instance Segmentation dataset","num_papers_in_archive":9},{"url":"/dataset/robust-mis","name":"ROBUST-MIS","full_name":"Robust Medical Instrument Segmentation Challenge 2019","num_papers_in_archive":8},{"url":"/dataset/tiktok-dataset","name":"TikTok Dataset","full_name":"Learning High Fidelity Depths of Dressed Humans  by Watching Social Media Dance Videos","num_papers_in_archive":8},{"url":"/dataset/ndd20","name":"NDD20","full_name":"Northumberland Dolphin Dataset 2020","num_papers_in_archive":7},{"url":"/dataset/kins","name":"KINS","full_name":"","num_papers_in_archive":6},{"url":"/dataset/lis","name":"LIS","full_name":"low-light instance segmentation","num_papers_in_archive":6},{"url":"/dataset/open-images-v7","name":"Open Images V7","full_name":"","num_papers_in_archive":6},{"url":"/dataset/shipsg","name":"ShipSG","full_name":"Ship Segmentation and Georeferencing Dataset","num_papers_in_archive":6},{"url":"/dataset/bup20","name":"BUP20","full_name":"Sweet Pepper 2020 University of Bonn","num_papers_in_archive":5},{"url":"/dataset/isbda","name":"ISBDA","full_name":"","num_papers_in_archive":5},{"url":"/dataset/nerds-360","name":"NERDS 360","full_name":"NeRF for Reconstruction, Decomposition and Scene Synthesis of 360° outdoor scenes","num_papers_in_archive":5},{"url":"/dataset/oodis","name":"OoDIS","full_name":"Anomaly Instance Segmentation Benchmark","num_papers_in_archive":5},{"url":"/dataset/spacenet-1","name":"SpaceNet 1","full_name":"SpaceNet 1: Building Detection v1","num_papers_in_archive":5},{"url":"/dataset/wgisd","name":"WGISD","full_name":"Embrapa Wine Grape Instance Segmentation Dataset","num_papers_in_archive":5},{"url":"/dataset/armbench","name":"ARMBench","full_name":"","num_papers_in_archive":4},{"url":"/dataset/fraunhofer-ipa-bin-picking","name":"Fraunhofer IPA Bin-Picking","full_name":"Fraunhofer IPA Bin-Picking","num_papers_in_archive":4},{"url":"/dataset/ishape","name":"iShape","full_name":"","num_papers_in_archive":4},{"url":"/dataset/separated-coco","name":"Separated COCO","full_name":"","num_papers_in_archive":4},{"url":"/dataset/texbig","name":"TexBiG","full_name":"Text-Bild-Gefüge","num_papers_in_archive":4},{"url":"/dataset/timberseg-1-0","name":"TimberSeg 1.0","full_name":"","num_papers_in_archive":4},{"url":"/dataset/usis10k","name":"USIS10K","full_name":"Large-scale Underwater Salient Instance Segmentation Dataset","num_papers_in_archive":4},{"url":"/dataset/wisdom","name":"WISDOM","full_name":"Warehouse Instance Segmentation Dataset for Object Manipulation","num_papers_in_archive":4},{"url":"/dataset/aircraft-context-dataset","name":"Aircraft Context Dataset","full_name":"","num_papers_in_archive":3},{"url":"/dataset/deepsportradar-v1","name":"DeepSportRadar-v1","full_name":"","num_papers_in_archive":3},{"url":"/dataset/grasp","name":"GraSP","full_name":"Holistic and Multi-Granular Surgical Scene Understanding of Prostatectomies","num_papers_in_archive":3},{"url":"/dataset/oam-tcd","name":"OAM-TCD","full_name":"","num_papers_in_archive":3},{"url":"/dataset/parcel2d-real","name":"Parcel2D Real","full_name":"","num_papers_in_archive":3},{"url":"/dataset/robotpush","name":"RobotPush","full_name":"RobotPush","num_papers_in_archive":3},{"url":"/dataset/uiis10k","name":"UIIS10K","full_name":"General Underwater Image Instance Segmentation dataset 10K","num_papers_in_archive":3},{"url":"/dataset/lindenthal-camera-traps","name":"Lindenthal Camera Traps","full_name":"","num_papers_in_archive":2},{"url":"/dataset/motfront","name":"MOTFront","full_name":"","num_papers_in_archive":2},{"url":"/dataset/mvtec-d2s","name":"MVTec D2S","full_name":"MVTec Densely Segmented Supermarket","num_papers_in_archive":2},{"url":"/dataset/occluded-coco","name":"Occluded COCO","full_name":"","num_papers_in_archive":2},{"url":"/dataset/omnicity","name":"OmniCity","full_name":"","num_papers_in_archive":2},{"url":"/dataset/parcel3d","name":"Parcel3D","full_name":"","num_papers_in_archive":2},{"url":"/dataset/plittersdorf","name":"Plittersdorf","full_name":"","num_papers_in_archive":2},{"url":"/dataset/sb20","name":"SB20","full_name":"Sugar Beet 2020 University of Bonn","num_papers_in_archive":2},{"url":"/dataset/tbbr","name":"TBBR","full_name":"Thermal Bridges on Building Rooftops","num_papers_in_archive":2},{"url":"/dataset/uw-indoor-scenes-uw-is-occluded-dataset","name":"UW Indoor Scenes (UW-IS) Occluded dataset","full_name":"","num_papers_in_archive":2},{"url":"/dataset/box-is","name":"Box-IS","full_name":"Box-IS","num_papers_in_archive":1},{"url":"/dataset/bpcis","name":"BPCIS","full_name":"Bacterial Phase Contrast for Instance Segementation","num_papers_in_archive":1},{"url":"/dataset/ccse","name":"CCSE","full_name":"Chinese Character Stroke Extraction","num_papers_in_archive":1},{"url":"/dataset/coco-n-medium","name":"COCO-N Medium","full_name":"","num_papers_in_archive":1},{"url":"/dataset/coco-wan-medium-noise","name":"COCO-WAN (Medium noise)","full_name":"Benchmarking Label Noise in Instance Segmentation: Spatial Noise Matters","num_papers_in_archive":1},{"url":"/dataset/dlo-instance-segmentation-dataset","name":"DLO Instance Segmentation dataset","full_name":"DLO Instance Segmentation dataset generated by Blender","num_papers_in_archive":1},{"url":"/dataset/enseg","name":"ENSeg","full_name":"","num_papers_in_archive":1},{"url":"/dataset/fashionfail","name":"FashionFail","full_name":"FashionFail","num_papers_in_archive":1},{"url":"/dataset/fraunhofer-ezrt-xxl-ct-instance-segmentation","name":"Fraunhofer EZRT XXL-CT Instance Segmentation Me163","full_name":"","num_papers_in_archive":1},{"url":"/dataset/graspclutter6d","name":"GraspClutter6D","full_name":"","num_papers_in_archive":1},{"url":"/dataset/guiss-dataset","name":"GUISS dataset","full_name":"Meshes, textures, Blend files, stereo datasets, depth maps, depth estimations)","num_papers_in_archive":1},{"url":"/dataset/hepic","name":"HePIC 🏛️","full_name":"","num_papers_in_archive":1},{"url":"/dataset/ht1080wt-cells-3d-collagen-type-i-matrices","name":"HT1080WT cells - 3D collagen type I matrices","full_name":"HT1080WT cells embedded in 3D collagen type I matrices - manual annotations for cell instance segmentation and tracking","num_papers_in_archive":1},{"url":"/dataset/icdar-2021-competition-on-historical-map","name":"ICDAR 2021","full_name":"","num_papers_in_archive":1},{"url":"/dataset/https-doi-org-10-4121-13603787-v2","name":"Image-based size estimation of broccoli heads under varying degrees of occlusion","full_name":"","num_papers_in_archive":1},{"url":"/dataset/ldd","name":"LDD","full_name":"LDD: A Grape Diseases Dataset Detection and Instance Segmentation","num_papers_in_archive":1},{"url":"/dataset/mis-check-dam","name":"MIS-Check Dam","full_name":"Minor Irrigation Structures- Check Dam","num_papers_in_archive":1},{"url":"/dataset/miscs","name":"MiSCS","full_name":"Microscopic Shrub Cross Sections","num_papers_in_archive":1},{"url":"/dataset/nyudv2-is","name":"NYUDv2-IS","full_name":"","num_papers_in_archive":1},{"url":"/dataset/object-centric-stylized-coco","name":"Object-Centric Stylized COCO","full_name":"","num_papers_in_archive":1},{"url":"/dataset/pwiseg","name":"PWISeg","full_name":"PWISeg Surgical Instruments Dataset","num_papers_in_archive":1},{"url":"/dataset/radiogalaxynet","name":"RadioGalaxyNET","full_name":"","num_papers_in_archive":1},{"url":"/dataset/radiogalaxynet-dataset","name":"RadioGalaxyNET Dataset","full_name":"","num_papers_in_archive":1},{"url":"/dataset/semanticsugarbeets","name":"SemanticSugarBeets","full_name":"","num_papers_in_archive":1},{"url":"/dataset/sesiv","name":"SESIV","full_name":"SEmantic Salient Instance Video","num_papers_in_archive":1},{"url":"/dataset/sun-rgbd-is","name":"SUN-RGBD-IS","full_name":"SUN-RGBD-IS","num_papers_in_archive":1},{"url":"/dataset/tampar","name":"TAMPAR","full_name":"","num_papers_in_archive":1},{"url":"/dataset/timbervision-dataset","name":"TimberVision","full_name":"TimberVision","num_papers_in_archive":1},{"url":"/dataset/tyc-dataset","name":"TYC Dataset","full_name":"The TYC Dataset for Understanding Instance-Level Semantics and Motions of Cells in Microstructures","num_papers_in_archive":1},{"url":"/dataset/uav-billboards","name":"UAVBillboards","full_name":"UAV Billboards","num_papers_in_archive":1},{"url":"/dataset/ufba-425","name":"UFBA-425","full_name":"","num_papers_in_archive":1},{"url":"/dataset/vizwiz-fewshot","name":"VizWiz-FewShot","full_name":"","num_papers_in_archive":1},{"url":"/dataset/yim-dataset","name":"YIM Dataset","full_name":"Yeast Cells in Microstructures Dataset","num_papers_in_archive":1},{"url":"/dataset/aachen-heerlen-annotated-steel-microstructure","name":"Aachen-Heerlen Annotated Steel Microstructure Dataset","full_name":"","num_papers_in_archive":0},{"url":"/dataset/cornhub","name":"CornHub","full_name":"Instance-Segmentation Dataset of Corn Cobs","num_papers_in_archive":0},{"url":"/dataset/multi-spectral-leaf-segmentation","name":"Multi-Spectral Leaf Segmentation","full_name":"Multi-Spectral Leaf Segmentation For Crop/Weed Identification","num_papers_in_archive":0},{"url":"/dataset/shiprsimagenet","name":"ShipRSImageNet","full_name":"","num_papers_in_archive":0}],"subtasks":[{"url":"/task/3d-instance-segmentation-1","name":"3D Instance Segmentation"},{"url":"/task/3d-semantic-instance-segmentation","name":"3D Semantic Instance Segmentation"},{"url":"/task/amodal-instance-segmentation","name":"Amodal Instance Segmentation"},{"url":"/task/anomaly-instance-segmentation","name":"Anomaly Instance Segmentation"},{"url":"/task/box-supervised-instance-segmentation","name":"Box-supervised Instance Segmentation"},{"url":"/task/human-instance-segmentation","name":"Human Instance Segmentation"},{"url":"/task/image-level-supervised-instance-segmentation","name":"Image-level Supervised Instance Segmentation"},{"url":"/task/one-shot-instance-segmentation","name":"One-Shot Instance Segmentation"},{"url":"/task/open-world-instance-segmentation","name":"Open-World Instance Segmentation"},{"url":"/task/point-supervised-instance-segmentation","name":"Point-Supervised Instance Segmentation"},{"url":"/task/real-time-instance-segmentation","name":"Real-time Instance Segmentation"},{"url":"/task/referring-expression-segmentation","name":"Referring Expression Segmentation"},{"url":"/task/rgb-d-instance-segmentation","name":"RGB-D Instance Segmentation"},{"url":"/task/semi-supervised-person-instance-segmentation","name":"Semi-Supervised Person Instance Segmentation"},{"url":"/task/solar-cell-segmentation","name":"Solar Cell Segmentation"},{"url":"/task/unseen-object-instance-segmentation","name":"Unseen Object Instance Segmentation"},{"url":"/task/unsupervised-object-segmentation","name":"Unsupervised Object Segmentation"}],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":1158,"tagged_in_all":2262,"items":[{"url":"/paper/mask-r-cnn","title":"Mask R-CNN","date":"2017-03-20","arxiv_id":"1703.06870","repositories_listed":179,"syntology":{"n":140,"n_ran":42,"n_unverified":98,"n_pointer_only":23}},{"url":"/paper/mmdetection-open-mmlab-detection-toolbox-and","title":"MMDetection: Open MMLab Detection Toolbox and Benchmark","date":"2019-06-17","arxiv_id":"1906.07155","repositories_listed":142,"syntology":{"n":82,"n_ran":14,"n_unverified":68,"n_pointer_only":0}},{"url":"/paper/swin-transformer-hierarchical-vision","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","date":"2021-03-25","arxiv_id":"2103.14030","repositories_listed":80,"syntology":{"n":207,"n_ran":108,"n_unverified":99,"n_pointer_only":43}},{"url":"/paper/yolact-real-time-instance-segmentation","title":"YOLACT: Real-time Instance Segmentation","date":"2019-04-04","arxiv_id":"1904.02689","repositories_listed":48,"syntology":{"n":21,"n_ran":10,"n_unverified":11,"n_pointer_only":6}},{"url":"/paper/190807919","title":"Deep High-Resolution Representation Learning for Visual Recognition","date":"2019-08-20","arxiv_id":"1908.07919","repositories_listed":42,"syntology":{"n":34,"n_ran":3,"n_unverified":31,"n_pointer_only":16}},{"url":"/paper/deep-high-resolution-representation-learning","title":"Deep High-Resolution Representation Learning for Human Pose Estimation","date":"2019-02-25","arxiv_id":"1902.09212","repositories_listed":39,"syntology":{"n":25,"n_ran":8,"n_unverified":17,"n_pointer_only":0}},{"url":"/paper/microsoft-coco-common-objects-in-context","title":"Microsoft COCO: Common Objects in Context","date":"2014-05-01","arxiv_id":"1405.0312","repositories_listed":38,"syntology":{"n":7,"n_ran":1,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/resnest-split-attention-networks","title":"ResNeSt: Split-Attention Networks","date":"2020-04-19","arxiv_id":"2004.08955","repositories_listed":36,"syntology":{"n":48,"n_ran":8,"n_unverified":40,"n_pointer_only":23}},{"url":"/paper/yolact-better-real-time-instance-segmentation","title":"YOLACT++: Better Real-time Instance Segmentation","date":"2019-12-03","arxiv_id":"1912.06218","repositories_listed":36,"syntology":{"n":43,"n_ran":11,"n_unverified":32,"n_pointer_only":0}},{"url":"/paper/res2net-a-new-multi-scale-backbone","title":"Res2Net: A New Multi-scale Backbone Architecture","date":"2019-04-02","arxiv_id":"1904.01169","repositories_listed":34,"syntology":{"n":9,"n_ran":3,"n_unverified":6,"n_pointer_only":9}},{"url":"/paper/non-local-neural-networks","title":"Non-local Neural Networks","date":"2017-11-21","arxiv_id":"1711.07971","repositories_listed":32,"syntology":{"n":4,"n_ran":3,"n_unverified":1,"n_pointer_only":4}},{"url":"/paper/deformable-convnets-v2-more-deformable-better","title":"Deformable ConvNets v2: More Deformable, Better Results","date":"2018-11-27","arxiv_id":"1811.11168","repositories_listed":26,"syntology":{"n":13,"n_ran":2,"n_unverified":11,"n_pointer_only":2}},{"url":"/paper/solo-segmenting-objects-by-locations","title":"SOLO: Segmenting Objects by Locations","date":"2019-12-10","arxiv_id":"1912.04488","repositories_listed":24,"syntology":null},{"url":"/paper/swin-transformer-v2-scaling-up-capacity-and","title":"Swin Transformer V2: Scaling Up Capacity and Resolution","date":"2021-11-18","arxiv_id":"2111.09883","repositories_listed":23,"syntology":{"n":30,"n_ran":3,"n_unverified":27,"n_pointer_only":0}},{"url":"/paper/towards-end-to-end-lane-detection-an-instance","title":"Towards End-to-End Lane Detection: an Instance Segmentation Approach","date":"2018-02-15","arxiv_id":"1802.05591","repositories_listed":22,"syntology":{"n":34,"n_ran":3,"n_unverified":31,"n_pointer_only":1}},{"url":"/paper/visual-attention-network","title":"Visual Attention Network","date":"2022-02-20","arxiv_id":"2202.09741","repositories_listed":21,"syntology":{"n":6,"n_ran":0,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/high-resolution-image-synthesis-and-semantic","title":"High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs","date":"2017-11-30","arxiv_id":"1711.11585","repositories_listed":21,"syntology":{"n":5,"n_ran":4,"n_unverified":1,"n_pointer_only":3}},{"url":"/paper/polyloss-a-polynomial-expansion-perspective-1","title":"PolyLoss: A Polynomial Expansion Perspective of Classification Loss Functions","date":"2022-04-26","arxiv_id":"2204.12511","repositories_listed":19,"syntology":{"n":7,"n_ran":1,"n_unverified":6,"n_pointer_only":1}},{"url":"/paper/multi-task-learning-using-uncertainty-to","title":"Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics","date":"2017-05-19","arxiv_id":"1705.07115","repositories_listed":19,"syntology":{"n":4,"n_ran":2,"n_unverified":2,"n_pointer_only":3}},{"url":"/paper/solov2-dynamic-faster-and-stronger","title":"SOLOv2: Dynamic and Fast Instance Segmentation","date":"2020-03-23","arxiv_id":"2003.10152","repositories_listed":18,"syntology":{"n":38,"n_ran":15,"n_unverified":23,"n_pointer_only":24}},{"url":"/paper/rtmdet-an-empirical-study-of-designing-real","title":"RTMDet: An Empirical Study of Designing Real-Time Object Detectors","date":"2022-12-14","arxiv_id":"2212.07784","repositories_listed":14,"syntology":{"n":20,"n_ran":3,"n_unverified":17,"n_pointer_only":0}},{"url":"/paper/pointrend-image-segmentation-as-rendering","title":"PointRend: Image Segmentation as Rendering","date":"2019-12-17","arxiv_id":"1912.08193","repositories_listed":14,"syntology":{"n":18,"n_ran":5,"n_unverified":13,"n_pointer_only":0}},{"url":"/paper/revisiting-foreground-background-imbalance-in","title":"Is Heuristic Sampling Necessary in Training Deep Object Detectors?","date":"2019-09-11","arxiv_id":"1909.04868","repositories_listed":14,"syntology":null},{"url":"/paper/factorized-attention-self-attention-with","title":"Efficient Attention: Attention with Linear Complexities","date":"2018-12-04","arxiv_id":"1812.01243","repositories_listed":14,"syntology":{"n":8,"n_ran":7,"n_unverified":1,"n_pointer_only":1}},{"url":"/paper/bottleneck-transformers-for-visual","title":"Bottleneck Transformers for Visual Recognition","date":"2021-01-27","arxiv_id":"2101.11605","repositories_listed":13,"syntology":{"n":49,"n_ran":26,"n_unverified":23,"n_pointer_only":8}},{"url":"/paper/unet-redesigning-skip-connections-to-exploit","title":"UNet++: Redesigning Skip Connections to Exploit Multiscale Features in Image Segmentation","date":"2019-12-11","arxiv_id":"1912.05074","repositories_listed":13,"syntology":{"n":9,"n_ran":1,"n_unverified":8,"n_pointer_only":2}},{"url":"/paper/spinenet-learning-scale-permuted-backbone-for","title":"SpineNet: Learning Scale-Permuted Backbone for Recognition and Localization","date":"2019-12-10","arxiv_id":"1912.05027","repositories_listed":13,"syntology":null},{"url":"/paper/eca-net-efficient-channel-attention-for-deep","title":"ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks","date":"2019-10-08","arxiv_id":"1910.03151","repositories_listed":13,"syntology":{"n":8,"n_ran":1,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/xcit-cross-covariance-image-transformers","title":"XCiT: Cross-Covariance Image Transformers","date":"2021-06-17","arxiv_id":"2106.09681","repositories_listed":12,"syntology":{"n":14,"n_ran":3,"n_unverified":11,"n_pointer_only":3}},{"url":"/paper/panoptic-feature-pyramid-networks","title":"Panoptic Feature Pyramid Networks","date":"2019-01-08","arxiv_id":"1901.02446","repositories_listed":12,"syntology":{"n":12,"n_ran":7,"n_unverified":5,"n_pointer_only":0}}],"syntology_records":27,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}