{"url":"/sota/dichotomous-image-segmentation-on-dis-te1","task":{"name":"Dichotomous Image Segmentation","url":"/task/dichotomous-image-segmentation","note":null},"dataset":{"name":"DIS-TE1","url":"/dataset/dis5k"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"Currently, existing image segmentation tasks mainly focus on segmenting objects with specific characteristics, e.g., salient, camouflaged, meticulous, or specific categories. Most of them have the same input/output formats, and barely use exclusive mechanisms designed for segmenting targets in their models, which means almost all tasks are dataset-dependent. Thus, it is very promising to formulate a category-agnostic DIS task for accurately segmenting objects with different structure complexities, regardless of their characteristics. Compared with semantic segmentation, the proposed DIS task usually focuses on images with single or a few targets, from which getting richer accurate details of each target is more feasible.","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":["max F-Measure","weighted F-measure","MAE","S-Measure","E-measure","HCE"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"max F-Measure":null,"weighted F-measure":null,"MAE":"lower","S-Measure":null,"E-measure":null,"HCE":null}},"counts":{"rows":22,"rows_with_code":22,"rows_with_paper_page":22,"rows_dated":22,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"PDFNet","metrics":{"E-measure":"0.927","MAE":"0.031","S-Measure":"0.899","max F-Measure":"0.890","weighted F-measure":"0.846"},"uses_additional_data":false,"paper_date":"2025-03-08","paper":"/paper/patch-depth-fusion-dichotomous-image","paper_url":"https://arxiv.org/abs/2503.06100v3","paper_title":"Patch-Depth Fusion: Dichotomous Image Segmentation via Fine-Grained Patch Strategy and Depth Integrity-Prior","code":"https://github.com/tennine2077/pdfnet","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"MVANet","metrics":{"E-measure":"0.911","HCE":"104","MAE":"0.037","S-Measure":"0.879","max F-Measure":"0.873","weighted F-measure":"0.823"},"uses_additional_data":false,"paper_date":"2024-04-11","paper":"/paper/multi-view-aggregation-network-for","paper_url":"https://arxiv.org/abs/2404.07445v1","paper_title":"Multi-view Aggregation Network for Dichotomous Image Segmentation","code":"https://github.com/qianyu-dlut/mvanet","n_code_links":1,"syntology":{"n_ran":8,"n_unverified":1,"n_samples":9,"n_pointer_only_licence":0}},{"rank_in_archive_order":3,"model":"BiRefNet","metrics":{"E-measure":"0.908","HCE":"106","MAE":"0.038","S-Measure":"0.882","max F-Measure":"0.855","weighted F-measure":"0.814"},"uses_additional_data":false,"paper_date":"2024-01-07","paper":"/paper/bilateral-reference-for-high-resolution","paper_url":"https://arxiv.org/abs/2401.03407v6","paper_title":"Bilateral Reference for High-Resolution Dichotomous Image Segmentation","code":"https://github.com/zhengpeng7/birefnet","n_code_links":1,"syntology":{"n_ran":13,"n_unverified":1,"n_samples":14,"n_pointer_only_licence":0}},{"rank_in_archive_order":4,"model":"InSPyReNet (HR scale)","metrics":{"E-measure":"0.894","HCE":"110","MAE":"0.045","S-Measure":"0.873","max F-Measure":"0.845","weighted F-measure":"0.788"},"uses_additional_data":false,"paper_date":"2022-09-20","paper":"/paper/revisiting-image-pyramid-structure-for-high","paper_url":"https://arxiv.org/abs/2209.09475v3","paper_title":"Revisiting Image Pyramid Structure for High Resolution Salient Object Detection","code":"https://github.com/plemeri/transparent-background","n_code_links":3,"syntology":{"n_ran":10,"n_unverified":1,"n_samples":11,"n_pointer_only_licence":0}},{"rank_in_archive_order":5,"model":"InSPyReNet","metrics":{"HCE":"148","S-Measure":"0.862","max F-Measure":"0.834"},"uses_additional_data":false,"paper_date":"2022-09-20","paper":"/paper/revisiting-image-pyramid-structure-for-high","paper_url":"https://arxiv.org/abs/2209.09475v3","paper_title":"Revisiting Image Pyramid Structure for High Resolution Salient Object Detection","code":"https://github.com/plemeri/transparent-background","n_code_links":3,"syntology":{"n_ran":10,"n_unverified":1,"n_samples":11,"n_pointer_only_licence":0}},{"rank_in_archive_order":6,"model":"IS-Net","metrics":{"E-measure":"0.820","HCE":"149","MAE":"0.074","S-Measure":"0.787","max F-Measure":"0.740","weighted F-measure":"0.662"},"uses_additional_data":false,"paper_date":"2022-03-06","paper":"/paper/highly-accurate-dichotomous-image","paper_url":"https://arxiv.org/abs/2203.03041v4","paper_title":"Highly Accurate Dichotomous Image Segmentation","code":"https://github.com/xuebinqin/DIS","n_code_links":1,"syntology":{"n_ran":9,"n_unverified":1,"n_samples":10,"n_pointer_only_licence":0}},{"rank_in_archive_order":7,"model":"HySM","metrics":{"E-measure":"0.803","HCE":"205","MAE":"0.082","S-Measure":"0.761","max F-Measure":"0.695","weighted F-measure":"0.597"},"uses_additional_data":false,"paper_date":"2020-12-21","paper":"/paper/hyperseg-patch-wise-hypernetwork-for-real","paper_url":"https://arxiv.org/abs/2012.11582v2","paper_title":"HyperSeg: Patch-wise Hypernetwork for Real-time Semantic Segmentation","code":"https://github.com/YuvalNirkin/hyperseg","n_code_links":1,"syntology":null},{"rank_in_archive_order":8,"model":"U2Net","metrics":{"E-measure":"0.801","HCE":"224","MAE":"0.083","S-Measure":"0.760","max F-Measure":"0.694","weighted F-measure":"0.601"},"uses_additional_data":false,"paper_date":"2020-05-18","paper":"/paper/u-2-net-going-deeper-with-nested-u-structure","paper_url":"https://arxiv.org/abs/2005.09007v3","paper_title":"U$^2$-Net: Going Deeper with Nested U-Structure for Salient Object Detection","code":"https://github.com/xuebinqin/U-2-Net","n_code_links":29,"syntology":{"n_ran":17,"n_unverified":25,"n_samples":42,"n_pointer_only_licence":2}},{"rank_in_archive_order":9,"model":"BASNet","metrics":{"E-measure":"0.801","HCE":"220","MAE":"0.084","S-Measure":"0.754","max F-Measure":"0.688","weighted F-measure":"0.595"},"uses_additional_data":false,"paper_date":"2019-06-01","paper":"/paper/basnet-boundary-aware-salient-object","paper_url":"http://openaccess.thecvf.com/content_CVPR_2019/html/Qin_BASNet_Boundary-Aware_Salient_Object_Detection_CVPR_2019_paper.html","paper_title":"BASNet: Boundary-Aware Salient Object Detection","code":"https://github.com/NathanUA/BASNet","n_code_links":3,"syntology":null},{"rank_in_archive_order":10,"model":"MBV3","metrics":{"E-measure":"0.818","HCE":"274","MAE":"0.083","S-Measure":"0.740","max F-Measure":"0.669","weighted F-measure":"0.595"},"uses_additional_data":false,"paper_date":"2019-05-06","paper":"/paper/searching-for-mobilenetv3","paper_url":"https://arxiv.org/abs/1905.02244v5","paper_title":"Searching for MobileNetV3","code":"https://github.com/tensorflow/models","n_code_links":67,"syntology":{"n_ran":83,"n_unverified":22,"n_samples":105,"n_pointer_only_licence":46}},{"rank_in_archive_order":11,"model":"HRNet","metrics":{"E-measure":"0.797","HCE":"262","MAE":"0.088","S-Measure":"0.742","max F-Measure":"0.668","weighted F-measure":"0.579"},"uses_additional_data":false,"paper_date":"2019-08-20","paper":"/paper/190807919","paper_url":"https://arxiv.org/abs/1908.07919v2","paper_title":"Deep High-Resolution Representation Learning for Visual Recognition","code":"https://github.com/open-mmlab/mmdetection","n_code_links":42,"syntology":{"n_ran":14,"n_unverified":20,"n_samples":34,"n_pointer_only_licence":16}},{"rank_in_archive_order":12,"model":"STDC","metrics":{"E-measure":"0.798","HCE":"249","MAE":"0.090","S-Measure":"0.723","max F-Measure":"0.648","weighted F-measure":"0.562"},"uses_additional_data":false,"paper_date":"2021-04-27","paper":"/paper/rethinking-bisenet-for-real-time-semantic","paper_url":"https://arxiv.org/abs/2104.13188v1","paper_title":"Rethinking BiSeNet For Real-time Semantic Segmentation","code":"https://github.com/PaddlePaddle/PaddleSeg","n_code_links":6,"syntology":{"n_ran":9,"n_unverified":7,"n_samples":16,"n_pointer_only_licence":0}},{"rank_in_archive_order":13,"model":"PFNet","metrics":{"E-measure":"0.786","HCE":"253","MAE":"0.094","S-Measure":"0.722","max F-Measure":"0.646","weighted F-measure":"0.552"},"uses_additional_data":false,"paper_date":"2021-04-21","paper":"/paper/camouflaged-object-segmentation-with","paper_url":"https://arxiv.org/abs/2104.10475v1","paper_title":"Camouflaged Object Segmentation with Distraction Mining","code":"https://github.com/Mhaiyang/CVPR2021_PFNet","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":5,"n_samples":9,"n_pointer_only_licence":9}},{"rank_in_archive_order":14,"model":"PSPNet","metrics":{"E-measure":"0.791","HCE":"267","MAE":"0.089","S-Measure":"0.725","max F-Measure":"0.645","weighted F-measure":"0.557"},"uses_additional_data":false,"paper_date":"2016-12-04","paper":"/paper/pyramid-scene-parsing-network","paper_url":"http://arxiv.org/abs/1612.01105v2","paper_title":"Pyramid Scene Parsing Network","code":"https://github.com/tensorflow/models","n_code_links":67,"syntology":{"n_ran":7,"n_unverified":22,"n_samples":29,"n_pointer_only_licence":5}},{"rank_in_archive_order":15,"model":"SINetV2","metrics":{"E-measure":"0.791","HCE":"274","MAE":"0.094","S-Measure":"0.727","max F-Measure":"0.644","weighted F-measure":"0.558"},"uses_additional_data":false,"paper_date":"2021-02-20","paper":"/paper/concealed-object-detection","paper_url":"https://arxiv.org/abs/2102.10274v2","paper_title":"Concealed Object Detection","code":"https://github.com/GewelsJI/SINet-V2","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":16,"model":"F3Net","metrics":{"E-measure":"0.783","HCE":"244","MAE":"0.095","S-Measure":"0.721","max F-Measure":"0.640","weighted F-measure":"0.549"},"uses_additional_data":false,"paper_date":"2019-11-26","paper":"/paper/f3net-fusion-feedback-and-focus-for-salient","paper_url":"https://arxiv.org/abs/1911.11445v1","paper_title":"F3Net: Fusion, Feedback and Focus for Salient Object Detection","code":"https://github.com/weijun88/F3Net","n_code_links":4,"syntology":null},{"rank_in_archive_order":17,"model":"ICNet","metrics":{"E-measure":"0.784","HCE":"234","MAE":"0.095","S-Measure":"0.716","max F-Measure":"0.631","weighted F-measure":"0.535"},"uses_additional_data":false,"paper_date":"2017-04-27","paper":"/paper/icnet-for-real-time-semantic-segmentation-on","paper_url":"http://arxiv.org/abs/1704.08545v2","paper_title":"ICNet for Real-Time Semantic Segmentation on High-Resolution Images","code":"https://github.com/osmr/imgclsmob","n_code_links":18,"syntology":null},{"rank_in_archive_order":18,"model":"UNet","metrics":{"E-measure":"0.750","HCE":"233","MAE":"0.106","S-Measure":"0.716","max F-Measure":"0.625","weighted F-measure":"0.514"},"uses_additional_data":false,"paper_date":"2015-05-18","paper":"/paper/u-net-convolutional-networks-for-biomedical","paper_url":"http://arxiv.org/abs/1505.04597v1","paper_title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","code":"https://github.com/labmlai/annotated_deep_learning_paper_implementations","n_code_links":487,"syntology":{"n_ran":518,"n_unverified":239,"n_samples":757,"n_pointer_only_licence":426}},{"rank_in_archive_order":19,"model":"GateNet","metrics":{"E-measure":"0.766","HCE":"230","MAE":"0.099","S-Measure":"0.701","max F-Measure":"0.620","weighted F-measure":"0.517"},"uses_additional_data":false,"paper_date":"2020-07-16","paper":"/paper/suppress-and-balance-a-simple-gated-network","paper_url":"https://arxiv.org/abs/2007.08074v3","paper_title":"Suppress and Balance: A Simple Gated Network for Salient Object Detection","code":"https://github.com/Xiaoqi-Zhao-DLUT/GateNet-RGB-Saliency","n_code_links":3,"syntology":null},{"rank_in_archive_order":20,"model":"DeeplabV3+","metrics":{"E-measure":"0.772","HCE":"234","MAE":"0.102","S-Measure":"0.694","max F-Measure":"0.601","weighted F-measure":"0.506"},"uses_additional_data":false,"paper_date":"2017-06-17","paper":"/paper/rethinking-atrous-convolution-for-semantic","paper_url":"http://arxiv.org/abs/1706.05587v3","paper_title":"Rethinking Atrous Convolution for Semantic Image Segmentation","code":"https://github.com/tensorflow/models","n_code_links":77,"syntology":{"n_ran":3,"n_unverified":4,"n_samples":7,"n_pointer_only_licence":3}},{"rank_in_archive_order":21,"model":"GCPANet","metrics":{"E-measure":"0.750","HCE":"271","MAE":"0.103","S-Measure":"0.705","max F-Measure":"0.598","weighted F-measure":"0.495"},"uses_additional_data":false,"paper_date":"2020-03-02","paper":"/paper/global-context-aware-progressive-aggregation","paper_url":"https://arxiv.org/abs/2003.00651v1","paper_title":"Global Context-Aware Progressive Aggregation Network for Salient Object Detection","code":"https://github.com/JosephChenHub/GCPANet","n_code_links":2,"syntology":{"n_ran":5,"n_unverified":8,"n_samples":13,"n_pointer_only_licence":13}},{"rank_in_archive_order":22,"model":"BSV1","metrics":{"E-measure":"0.741","HCE":"288","MAE":"0.108","S-Measure":"0.695","max F-Measure":"0.595","weighted F-measure":"0.474"},"uses_additional_data":false,"paper_date":"2018-08-02","paper":"/paper/bisenet-bilateral-segmentation-network-for","paper_url":"http://arxiv.org/abs/1808.00897v1","paper_title":"BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation","code":"https://github.com/PaddlePaddle/PaddleSeg","n_code_links":21,"syntology":{"n_ran":7,"n_unverified":11,"n_samples":18,"n_pointer_only_licence":1}}],"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,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,885 of the 9,623 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9623,"papers_checked":6885,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":2737},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-25T09:33:49+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":16,"rows_with_any_sample_ran":16,"distinct_papers_with_graph_line":15,"distinct_papers_with_any_sample_ran":15,"samples_over_distinct_papers":{"n_ran":710,"n_unverified":367,"n_samples":1077,"n_pointer_only_licence":521,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":720,"n_unverified":368,"n_samples":1088,"n_pointer_only_licence":521,"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"}}}