{"url":"/sota/instance-segmentation-on-coco-2017-val","task":{"name":"Instance Segmentation","url":"/task/instance-segmentation","note":null},"dataset":{"name":"COCO 2017 val","url":null},"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*","mask AP","AP"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"mask AP*":"higher","mask AP":"higher","AP":"higher"}},"counts":{"rows":4,"rows_with_code":4,"rows_with_paper_page":4,"rows_dated":4,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"SparK (ConvNeXt V1-B Mask R-CNN)","metrics":{"AP":"45.1","mask AP":"45.1","mask AP*":"45.1"},"uses_additional_data":false,"paper_date":"2023-01-09","paper":"/paper/designing-bert-for-convolutional-networks","paper_url":"https://arxiv.org/abs/2301.03580v2","paper_title":"Designing BERT for Convolutional Networks: Sparse and Hierarchical Masked Modeling","code":"https://github.com/keyu-tian/spark","n_code_links":2,"syntology":{"n_ran":5,"n_unverified":9,"n_samples":14,"n_pointer_only_licence":0}},{"rank_in_archive_order":2,"model":"Mask Transfiner (R50-FPN)","metrics":{"mask AP*":"43.1"},"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,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":3,"model":"PointRend (MaskR-CNN, ResNet-50-FPN)","metrics":{"mask AP*":"39.7"},"uses_additional_data":false,"paper_date":"2019-12-17","paper":"/paper/pointrend-image-segmentation-as-rendering","paper_url":"https://arxiv.org/abs/1912.08193v2","paper_title":"PointRend: Image Segmentation as Rendering","code":"https://github.com/facebookresearch/detectron2/tree/master/projects/PointRend","n_code_links":14,"syntology":{"n_ran":5,"n_unverified":13,"n_samples":18,"n_pointer_only_licence":0}},{"rank_in_archive_order":4,"model":"RF-ConvNeXt-T Cascade R-CNN","metrics":{"AP":"44.3"},"uses_additional_data":false,"paper_date":"2022-06-14","paper":"/paper/rf-next-efficient-receptive-field-search-for","paper_url":"https://arxiv.org/abs/2206.06637v2","paper_title":"RF-Next: Efficient Receptive Field Search for Convolutional Neural Networks","code":"https://github.com/ShangHua-Gao/G2L-search","n_code_links":2,"syntology":{"n_ran":2,"n_unverified":1,"n_samples":3,"n_pointer_only_licence":3}}],"since_archive":{"present":false,"note":"No Syntology-extracted rows are published in this build."},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N 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).","rows_with_graph_line":4,"rows_with_any_sample_ran":4,"distinct_papers_with_graph_line":4,"distinct_papers_with_any_sample_ran":4,"samples_over_distinct_papers":{"n_ran":13,"n_unverified":23,"n_samples":36,"n_pointer_only_licence":3,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":13,"n_unverified":23,"n_samples":36,"n_pointer_only_licence":3,"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"}}}