{"url":"/sota/instance-segmentation-on-cityscapes-val","task":{"name":"Instance Segmentation","url":"/task/instance-segmentation","note":null},"dataset":{"name":"Cityscapes val","url":"/dataset/cityscapes"},"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","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","AP50":null,"AP":"higher"}},"counts":{"rows":17,"rows_with_code":17,"rows_with_paper_page":17,"rows_dated":17,"rows_using_additional_data":4},"rows":[{"rank_in_archive_order":1,"model":"ViT-P (OneFormer, ConvNeXt-L, single-scale, 512x1024, Mapillary Vistas-pretrained)","metrics":{"AP":"49.0","mask AP":"49.0"},"uses_additional_data":true,"paper_date":"2025-05-26","paper":"/paper/the-missing-point-in-vision-transformers-for","paper_url":"https://arxiv.org/abs/2505.19795v1","paper_title":"The Missing Point in Vision Transformers for Universal Image Segmentation","code":"https://github.com/sajjad-sh33/vit-p","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"OneFormer (ConvNeXt-L, single-scale, Mapillary-Pretrained)","metrics":{"mask AP":"48.7"},"uses_additional_data":true,"paper_date":"2022-11-10","paper":"/paper/oneformer-one-transformer-to-rule-universal","paper_url":"https://arxiv.org/abs/2211.06220v2","paper_title":"OneFormer: One Transformer to Rule Universal Image Segmentation","code":"https://github.com/huggingface/transformers","n_code_links":4,"syntology":{"n_ran":0,"n_unverified":5,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":3,"model":"OpenSeeD( SwinL, single-scale)","metrics":{"mask AP":"48.5"},"uses_additional_data":true,"paper_date":"2023-03-14","paper":"/paper/a-simple-framework-for-open-vocabulary","paper_url":"https://arxiv.org/abs/2303.08131v3","paper_title":"A Simple Framework for Open-Vocabulary Segmentation and Detection","code":"https://github.com/microsoft/X-Decoder","n_code_links":2,"syntology":null},{"rank_in_archive_order":4,"model":"AFF-Base (single-scale, point-based Mask2Former)","metrics":{"AP50":"74.2","mask AP":"46.2"},"uses_additional_data":false,"paper_date":"2023-04-24","paper":"/paper/autofocusformer-image-segmentation-off-the","paper_url":"https://arxiv.org/abs/2304.12406v2","paper_title":"AutoFocusFormer: Image Segmentation off the Grid","code":"https://github.com/apple/ml-autofocusformer","n_code_links":1,"syntology":null},{"rank_in_archive_order":5,"model":"OneFormer (DiNAT-L, single-scale)","metrics":{"mask AP":"45.6"},"uses_additional_data":false,"paper_date":"2022-11-10","paper":"/paper/oneformer-one-transformer-to-rule-universal","paper_url":"https://arxiv.org/abs/2211.06220v2","paper_title":"OneFormer: One Transformer to Rule Universal Image Segmentation","code":"https://github.com/huggingface/transformers","n_code_links":4,"syntology":{"n_ran":0,"n_unverified":5,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":6,"model":"OneFormer (Swin-L, single-scale)","metrics":{"mask AP":"45.6"},"uses_additional_data":false,"paper_date":"2022-11-10","paper":"/paper/oneformer-one-transformer-to-rule-universal","paper_url":"https://arxiv.org/abs/2211.06220v2","paper_title":"OneFormer: One Transformer to Rule Universal Image Segmentation","code":"https://github.com/huggingface/transformers","n_code_links":4,"syntology":{"n_ran":0,"n_unverified":5,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":7,"model":"DiNAT-L (single-scale, Mask2Former)","metrics":{"AP50":"72.6","mask AP":"45.1"},"uses_additional_data":false,"paper_date":"2022-09-29","paper":"/paper/dilated-neighborhood-attention-transformer","paper_url":"https://arxiv.org/abs/2209.15001v3","paper_title":"Dilated Neighborhood Attention Transformer","code":"https://github.com/huggingface/transformers","n_code_links":7,"syntology":null},{"rank_in_archive_order":8,"model":"AFF-Small (single-scale, point-based Mask2Former)","metrics":{"AP50":"72.8","mask AP":"44.0"},"uses_additional_data":false,"paper_date":"2023-04-24","paper":"/paper/autofocusformer-image-segmentation-off-the","paper_url":"https://arxiv.org/abs/2304.12406v2","paper_title":"AutoFocusFormer: Image Segmentation off the Grid","code":"https://github.com/apple/ml-autofocusformer","n_code_links":1,"syntology":null},{"rank_in_archive_order":9,"model":"Mask2Former (Swin-L, single-scale)","metrics":{"mask AP":"43.7"},"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,"syntology":{"n_ran":2,"n_unverified":6,"n_samples":8,"n_pointer_only_licence":0}},{"rank_in_archive_order":10,"model":"Mask2Former (Swin-B)","metrics":{"mask AP":"42"},"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,"syntology":{"n_ran":2,"n_unverified":6,"n_samples":8,"n_pointer_only_licence":0}},{"rank_in_archive_order":11,"model":"Mask2Former (Swin-S)","metrics":{"mask AP":"41.8"},"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,"syntology":{"n_ran":2,"n_unverified":6,"n_samples":8,"n_pointer_only_licence":0}},{"rank_in_archive_order":12,"model":"PolySnake","metrics":{"mask AP":"40.2"},"uses_additional_data":false,"paper_date":"2023-01-21","paper":"/paper/recurrent-contour-based-instance-segmentation","paper_url":"https://arxiv.org/abs/2301.08898v3","paper_title":"Recurrent Generic Contour-based Instance Segmentation with Progressive Learning","code":"https://github.com/fh2019ustc/polysnake","n_code_links":1,"syntology":null},{"rank_in_archive_order":13,"model":"Mask2Former (Swin-T)","metrics":{"mask AP":"39.7"},"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,"syntology":{"n_ran":2,"n_unverified":6,"n_samples":8,"n_pointer_only_licence":0}},{"rank_in_archive_order":14,"model":"Mask2Former (ResNet-101)","metrics":{"mask AP":"38.5"},"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,"syntology":{"n_ran":2,"n_unverified":6,"n_samples":8,"n_pointer_only_licence":0}},{"rank_in_archive_order":15,"model":"Mask2Former (ResNet-50)","metrics":{"mask AP":"37.4"},"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,"syntology":{"n_ran":2,"n_unverified":6,"n_samples":8,"n_pointer_only_licence":0}},{"rank_in_archive_order":16,"model":"GAIS-Net","metrics":{"mask AP":"37.1"},"uses_additional_data":true,"paper_date":"2020-06-14","paper":"/paper/geometry-aware-instance-segmentation-with","paper_url":"https://arxiv.org/abs/2006.07802v2","paper_title":"Geometry-Aware Instance Segmentation with Disparity Maps","code":"https://github.com/choyingw/GAIS-Net","n_code_links":1,"syntology":null},{"rank_in_archive_order":17,"model":"PointRend","metrics":{"mask AP":"35.8"},"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}}],"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":10,"rows_with_any_sample_ran":7,"distinct_papers_with_graph_line":3,"distinct_papers_with_any_sample_ran":2,"samples_over_distinct_papers":{"n_ran":7,"n_unverified":24,"n_samples":31,"n_pointer_only_licence":0,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":17,"n_unverified":64,"n_samples":81,"n_pointer_only_licence":0,"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"}}}