{"url":"/task/real-time-instance-segmentation","name":"Real-time Instance Segmentation","slug":"real-time-instance-segmentation","description_markdown":"Similar to its parent task, instance segmentation, but with the goal of achieving real-time capabilities under a defined setting.\r\n\r\nImage Credit: [SipMask: Spatial Information Preservation for Fast Image and Video Instance Segmentation](https://arxiv.org/pdf/2007.14772v1.pdf)","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":29,"papers_with_code":22,"benchmarks":8,"benchmark_tables_in_archive":8,"benchmark_tables_shown":8,"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":6,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/real-time-instance-segmentation-on-mscoco","slug":"real-time-instance-segmentation-on-mscoco","dataset":"MSCOCO","dataset_url":"/dataset/mscoco","rows_in_archive":22,"metrics":["mask AP","AP50","AP75","APS","APM","APL","Frame (fps)"],"first_row_in_archive_order":{"model":"RTMDet-Ins-x","paper_title":"RTMDet: An Empirical Study of Designing Real-Time Object Detectors","paper_url":"/paper/rtmdet-an-empirical-study-of-designing-real","paper_date":"2022-12-14","arxiv_id":"2212.07784","code_links":[{"title":"open-mmlab/mmdetection","url":"https://github.com/open-mmlab/mmdetection/tree/3.x/configs/rtmdet"},{"title":"open-mmlab/mmyolo","url":"https://github.com/open-mmlab/mmyolo"},{"title":"open-mmlab/mmrotate","url":"https://github.com/open-mmlab/mmrotate"},{"title":"open-edge-platform/training_extensions","url":"https://github.com/open-edge-platform/training_extensions"},{"title":"PaddlePaddle/PaddleYOLO","url":"https://github.com/PaddlePaddle/PaddleYOLO"},{"title":"open-edge-platform/geti","url":"https://github.com/open-edge-platform/geti"},{"title":"yxb-nku/strip-r-cnn","url":"https://github.com/yxb-nku/strip-r-cnn"},{"title":"HVision-NKU/Strip-R-CNN","url":"https://github.com/HVision-NKU/Strip-R-CNN"},{"title":"fiveai/MoCaE","url":"https://github.com/fiveai/MoCaE"},{"title":"yuyi1005/point2rbox-mmrotate","url":"https://github.com/yuyi1005/point2rbox-mmrotate"},{"title":"cszzshi/SimD","url":"https://github.com/cszzshi/SimD"},{"title":"CycloneBoy/PPDetectionPytorch","url":"https://github.com/CycloneBoy/PPDetectionPytorch"},{"title":"V3Det/mmdetection-V3Det","url":"https://github.com/V3Det/mmdetection-V3Det"},{"title":"RangiLyu/mmdetection_test","url":"https://github.com/RangiLyu/mmdetection_test"}],"syntology":{"n":20,"n_ran":3,"n_unverified":17,"n_pointer_only":0}}},{"leaderboard":"/sota/real-time-instance-segmentation-on-pascal-voc","slug":"real-time-instance-segmentation-on-pascal-voc","dataset":"PASCAL VOC 2012","dataset_url":null,"rows_in_archive":3,"metrics":["avgAP (mask AP + box AP)","boxAP","maskAP","FLOPs (G)","Size (M)","Frame (fps)"],"first_row_in_archive_order":{"model":"RAMEM UPANet80 V2","paper_title":"Real-time Automatic M-mode Echocardiography Measurement with Panel Attention from Local-to-Global Pixels","paper_url":"/paper/real-time-automatic-m-mode-echocardiography","paper_date":"2023-08-15","arxiv_id":"2308.07717","code_links":[{"title":"hanktseng131415go/ramem","url":"https://github.com/hanktseng131415go/ramem"}],"syntology":null}},{"leaderboard":"/sota/real-time-instance-segmentation-on-meis","slug":"real-time-instance-segmentation-on-meis","dataset":"MEIS","dataset_url":"/dataset/meis","rows_in_archive":2,"metrics":["FLOPs (G)","Frame (fps)","Size (M)","avgAP (mask AP + box AP)","boxAP","maskAP"],"first_row_in_archive_order":{"model":"maYOLACT ResNet50","paper_title":"Real-time Automatic M-mode Echocardiography Measurement with Panel Attention from Local-to-Global Pixels","paper_url":"/paper/real-time-automatic-m-mode-echocardiography","paper_date":"2023-08-15","arxiv_id":"2308.07717","code_links":[{"title":"hanktseng131415go/ramem","url":"https://github.com/hanktseng131415go/ramem"}],"syntology":null}},{"leaderboard":"/sota/real-time-instance-segmentation-on-cityscapes","slug":"real-time-instance-segmentation-on-cityscapes","dataset":"Cityscapes test","dataset_url":"/dataset/cityscapes","rows_in_archive":1,"metrics":["AP"],"first_row_in_archive_order":{"model":"CenterPoly","paper_title":"CenterPoly: real-time instance segmentation using bounding polygons","paper_url":"/paper/centerpoly-real-time-instance-segmentation","paper_date":"2021-08-19","arxiv_id":"2108.08923","code_links":[{"title":"hu64/centerpoly","url":"https://github.com/hu64/centerpoly"}],"syntology":null}},{"leaderboard":"/sota/real-time-instance-segmentation-on-india","slug":"real-time-instance-segmentation-on-india","dataset":"India Driving Dataset","dataset_url":null,"rows_in_archive":1,"metrics":["AP"],"first_row_in_archive_order":{"model":"CenterPoly","paper_title":"CenterPoly: real-time instance segmentation using bounding polygons","paper_url":"/paper/centerpoly-real-time-instance-segmentation","paper_date":"2021-08-19","arxiv_id":"2108.08923","code_links":[{"title":"hu64/centerpoly","url":"https://github.com/hu64/centerpoly"}],"syntology":null}},{"leaderboard":"/sota/real-time-instance-segmentation-on-kitti","slug":"real-time-instance-segmentation-on-kitti","dataset":"KITTI","dataset_url":"/dataset/kitti","rows_in_archive":1,"metrics":["AP"],"first_row_in_archive_order":{"model":"CenterPoly","paper_title":"CenterPoly: real-time instance segmentation using bounding polygons","paper_url":"/paper/centerpoly-real-time-instance-segmentation","paper_date":"2021-08-19","arxiv_id":"2108.08923","code_links":[{"title":"hu64/centerpoly","url":"https://github.com/hu64/centerpoly"}],"syntology":null}},{"leaderboard":"/sota/real-time-instance-segmentation-on-mscoco-1k","slug":"real-time-instance-segmentation-on-mscoco-1k","dataset":"MSCOCO-1k","dataset_url":"/dataset/coco","rows_in_archive":1,"metrics":["APM"],"first_row_in_archive_order":{"model":"RTMDet-Ins-x","paper_title":"RTMDet: An Empirical Study of Designing Real-Time Object Detectors","paper_url":"/paper/rtmdet-an-empirical-study-of-designing-real","paper_date":"2022-12-14","arxiv_id":"2212.07784","code_links":[{"title":"open-mmlab/mmdetection","url":"https://github.com/open-mmlab/mmdetection/tree/3.x/configs/rtmdet"},{"title":"open-mmlab/mmyolo","url":"https://github.com/open-mmlab/mmyolo"},{"title":"open-mmlab/mmrotate","url":"https://github.com/open-mmlab/mmrotate"},{"title":"open-edge-platform/training_extensions","url":"https://github.com/open-edge-platform/training_extensions"},{"title":"PaddlePaddle/PaddleYOLO","url":"https://github.com/PaddlePaddle/PaddleYOLO"},{"title":"open-edge-platform/geti","url":"https://github.com/open-edge-platform/geti"},{"title":"yxb-nku/strip-r-cnn","url":"https://github.com/yxb-nku/strip-r-cnn"},{"title":"HVision-NKU/Strip-R-CNN","url":"https://github.com/HVision-NKU/Strip-R-CNN"},{"title":"fiveai/MoCaE","url":"https://github.com/fiveai/MoCaE"},{"title":"yuyi1005/point2rbox-mmrotate","url":"https://github.com/yuyi1005/point2rbox-mmrotate"},{"title":"cszzshi/SimD","url":"https://github.com/cszzshi/SimD"},{"title":"CycloneBoy/PPDetectionPytorch","url":"https://github.com/CycloneBoy/PPDetectionPytorch"},{"title":"V3Det/mmdetection-V3Det","url":"https://github.com/V3Det/mmdetection-V3Det"},{"title":"RangiLyu/mmdetection_test","url":"https://github.com/RangiLyu/mmdetection_test"}],"syntology":{"n":20,"n_ran":3,"n_unverified":17,"n_pointer_only":0}}},{"leaderboard":"/sota/real-time-instance-segmentation-on-multi30k","slug":"real-time-instance-segmentation-on-multi30k","dataset":"multi30k_test_2017_mscoco","dataset_url":"/dataset/multi30k","rows_in_archive":1,"metrics":["mask AP"],"first_row_in_archive_order":{"model":"RTMDet-Ins-s","paper_title":"RTMDet: An Empirical Study of Designing Real-Time Object Detectors","paper_url":"/paper/rtmdet-an-empirical-study-of-designing-real","paper_date":"2022-12-14","arxiv_id":"2212.07784","code_links":[{"title":"open-mmlab/mmdetection","url":"https://github.com/open-mmlab/mmdetection/tree/3.x/configs/rtmdet"},{"title":"open-mmlab/mmyolo","url":"https://github.com/open-mmlab/mmyolo"},{"title":"open-mmlab/mmrotate","url":"https://github.com/open-mmlab/mmrotate"},{"title":"open-edge-platform/training_extensions","url":"https://github.com/open-edge-platform/training_extensions"},{"title":"PaddlePaddle/PaddleYOLO","url":"https://github.com/PaddlePaddle/PaddleYOLO"},{"title":"open-edge-platform/geti","url":"https://github.com/open-edge-platform/geti"},{"title":"yxb-nku/strip-r-cnn","url":"https://github.com/yxb-nku/strip-r-cnn"},{"title":"HVision-NKU/Strip-R-CNN","url":"https://github.com/HVision-NKU/Strip-R-CNN"},{"title":"fiveai/MoCaE","url":"https://github.com/fiveai/MoCaE"},{"title":"yuyi1005/point2rbox-mmrotate","url":"https://github.com/yuyi1005/point2rbox-mmrotate"},{"title":"cszzshi/SimD","url":"https://github.com/cszzshi/SimD"},{"title":"CycloneBoy/PPDetectionPytorch","url":"https://github.com/CycloneBoy/PPDetectionPytorch"},{"title":"V3Det/mmdetection-V3Det","url":"https://github.com/V3Det/mmdetection-V3Det"},{"title":"RangiLyu/mmdetection_test","url":"https://github.com/RangiLyu/mmdetection_test"}],"syntology":{"n":20,"n_ran":3,"n_unverified":17,"n_pointer_only":0}}}],"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/kitti","name":"KITTI","full_name":"","num_papers_in_archive":3661},{"url":"/dataset/multi30k","name":"Multi30K","full_name":"","num_papers_in_archive":139},{"url":"/dataset/mscoco","name":"MSCOCO","full_name":"","num_papers_in_archive":90},{"url":"/dataset/meis","name":"MEIS","full_name":"M-mode Echocardiograms for Instance Segmentation","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[{"url":"/task/instance-segmentation","name":"Instance Segmentation"}],"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":22,"of":22,"tagged_in_all":29,"items":[{"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/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/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/blendmask-top-down-meets-bottom-up-for","title":"BlendMask: Top-Down Meets Bottom-Up for Instance Segmentation","date":"2020-01-02","arxiv_id":"2001.00309","repositories_listed":9,"syntology":null},{"url":"/paper/centermask-real-time-anchor-free-instance-1","title":"CenterMask : Real-Time Anchor-Free Instance Segmentation","date":"2019-11-15","arxiv_id":"1911.06667","repositories_listed":8,"syntology":{"n":2,"n_ran":1,"n_unverified":1,"n_pointer_only":2}},{"url":"/paper/sparse-instance-activation-for-real-time","title":"Sparse Instance Activation for Real-Time Instance Segmentation","date":"2022-03-24","arxiv_id":"2203.12827","repositories_listed":2,"syntology":{"n":11,"n_ran":3,"n_unverified":8,"n_pointer_only":0}},{"url":"/paper/yolactedge-real-time-instance-segmentation-on","title":"YolactEdge: Real-time Instance Segmentation on the Edge","date":"2020-12-22","arxiv_id":"2012.12259","repositories_listed":2,"syntology":null},{"url":"/paper/centerdisks-real-time-instance-segmentation","title":"CenterDisks: Real-time instance segmentation with disk covering","date":"2024-03-05","arxiv_id":"2403.03296","repositories_listed":1,"syntology":null},{"url":"/paper/real-time-automatic-m-mode-echocardiography","title":"Real-time Automatic M-mode Echocardiography Measurement with Panel Attention from Local-to-Global Pixels","date":"2023-08-15","arxiv_id":"2308.07717","repositories_listed":1,"syntology":null},{"url":"/paper/real-time-instance-segmentation-with-polygons","title":"Real-time instance segmentation with polygons using an Intersection-over-Union loss","date":"2023-05-09","arxiv_id":"2305.05490","repositories_listed":1,"syntology":null},{"url":"/paper/fastinst-a-simple-query-based-model-for-real","title":"FastInst: A Simple Query-Based Model for Real-Time Instance Segmentation","date":"2023-03-15","arxiv_id":"2303.08594","repositories_listed":1,"syntology":{"n":9,"n_ran":2,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/d-inloc-indoor-localization-in-dynamic","title":"D-InLoc++: Indoor Localization in Dynamic Environments","date":"2022-09-21","arxiv_id":"2209.10185","repositories_listed":1,"syntology":null},{"url":"/paper/mask-aware-iou-for-anchor-assignment-in-real","title":"Mask-aware IoU for Anchor Assignment in Real-time Instance Segmentation","date":"2021-10-19","arxiv_id":"2110.09734","repositories_listed":1,"syntology":null},{"url":"/paper/centerpoly-real-time-instance-segmentation","title":"CenterPoly: real-time instance segmentation using bounding polygons","date":"2021-08-19","arxiv_id":"2108.08923","repositories_listed":1,"syntology":null},{"url":"/paper/real-time-instance-segmentation-with","title":"Real-time Instance Segmentation with Discriminative Orientation Maps","date":"2021-06-23","arxiv_id":"2106.12204","repositories_listed":1,"syntology":null},{"url":"/paper/deep-occlusion-aware-instance-segmentation","title":"Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers","date":"2021-03-23","arxiv_id":"2103.12340","repositories_listed":1,"syntology":{"n":12,"n_ran":7,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/sipmask-spatial-information-preservation-for","title":"SipMask: Spatial Information Preservation for Fast Image and Video Instance Segmentation","date":"2020-07-29","arxiv_id":"2007.14772","repositories_listed":1,"syntology":null},{"url":"/paper/centermask-real-time-anchor-free-instance-3","title":"CenterMask: Real-Time Anchor-Free Instance Segmentation","date":"2020-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/deep-snake-for-real-time-instance","title":"Deep Snake for Real-Time Instance Segmentation","date":"2020-01-06","arxiv_id":"2001.01629","repositories_listed":1,"syntology":null},{"url":"/paper/explicit-shape-encoding-for-real-time","title":"Explicit Shape Encoding for Real-Time Instance Segmentation","date":"2019-08-12","arxiv_id":"1908.04067","repositories_listed":1,"syntology":null},{"url":"/paper/straight-to-shapes-real-time-instance","title":"Straight to Shapes++: Real-time Instance Segmentation Made More Accurate","date":"2019-05-27","arxiv_id":"1905.11358","repositories_listed":1,"syntology":null}],"syntology_records":8,"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"}}