{"url":"/sota/rgb-d-salient-object-detection-on-sip","task":{"name":"RGB-D Salient Object Detection","url":"/task/rgb-d-salient-object-detection","note":null},"dataset":{"name":"SIP","url":"/dataset/sip"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"RGB-D Salient object detection (SOD) aims at distinguishing the most visually distinctive objects or regions in a scene from the given RGB and Depth data. It has a wide range of applications, including video/image segmentation, object recognition, visual tracking, foreground maps evaluation, image retrieval, content-aware image editing, information discovery, photosynthesis, and weakly\r\nsupervised semantic segmentation. Here, depth information plays an important complementary role in finding salient objects. Online benchmark: http://dpfan.net/d3netbenchmark.\r\n\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [Rethinking RGB-D Salient Object Detection: Models, Data Sets, and Large-Scale Benchmarks, TNNLS20](https://ieeexplore.ieee.org/abstract/document/9107477) )</span>","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":["S-Measure","Average MAE","max E-Measure","max F-Measure"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"S-Measure":null,"Average MAE":"lower","max E-Measure":null,"max F-Measure":null}},"counts":{"rows":16,"rows_with_code":16,"rows_with_paper_page":16,"rows_dated":16,"rows_using_additional_data":2},"rows":[{"rank_in_archive_order":1,"model":"DFormer-L","metrics":{"Average MAE":"0.032","S-Measure":"91.5","max E-Measure":"95.0","max F-Measure":"93.8"},"uses_additional_data":false,"paper_date":"2023-09-18","paper":"/paper/dformer-rethinking-rgbd-representation","paper_url":"https://arxiv.org/abs/2309.09668v2","paper_title":"DFormer: Rethinking RGBD Representation Learning for Semantic Segmentation","code":"https://github.com/VCIP-RGBD/DFormer","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"VST","metrics":{"Average MAE":"0.040","S-Measure":"90.4","max E-Measure":"94.4","max F-Measure":"91.5"},"uses_additional_data":false,"paper_date":"2021-04-25","paper":"/paper/visual-saliency-transformer","paper_url":"https://arxiv.org/abs/2104.12099v2","paper_title":"Visual Saliency Transformer","code":"https://github.com/nnizhang/VST","n_code_links":2,"syntology":{"n_ran":7,"n_unverified":4,"n_samples":11,"n_pointer_only_licence":11}},{"rank_in_archive_order":3,"model":"BTS-Net","metrics":{"Average MAE":"0.044","S-Measure":"89.6","max E-Measure":"93.3","max F-Measure":"90.1"},"uses_additional_data":false,"paper_date":"2021-04-05","paper":"/paper/bts-net-bi-directional-transfer-and-selection","paper_url":"https://arxiv.org/abs/2104.01784v1","paper_title":"BTS-Net: Bi-directional Transfer-and-Selection Network For RGB-D Salient Object Detection","code":"https://github.com/zwbx/BTS-Net","n_code_links":1,"syntology":null},{"rank_in_archive_order":4,"model":"CoLANet","metrics":{"Average MAE":"0.042","S-Measure":"89.5","max E-Measure":"93.5","max F-Measure":"89.4"},"uses_additional_data":false,"paper_date":"2024-07-09","paper":"/paper/cola-conditional-dropout-and-language-driven","paper_url":"https://arxiv.org/abs/2407.06780v1","paper_title":"CoLA: Conditional Dropout and Language-driven Robust Dual-modal Salient Object Detection","code":"https://github.com/ssecv/CoLA","n_code_links":1,"syntology":{"n_ran":8,"n_unverified":3,"n_samples":11,"n_pointer_only_licence":0}},{"rank_in_archive_order":5,"model":"SPSN","metrics":{"Average MAE":"0.042","S-Measure":"89.2","max E-Measure":"93.4","max F-Measure":"89.9"},"uses_additional_data":false,"paper_date":"2022-07-16","paper":"/paper/spsn-superpixel-prototype-sampling-network","paper_url":"https://arxiv.org/abs/2207.07898v1","paper_title":"SPSN: Superpixel Prototype Sampling Network for RGB-D Salient Object Detection","code":"https://github.com/Hydragon516/SPSN","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":1,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":6,"model":"JL-DCF*","metrics":{"Average MAE":"0.046","S-Measure":"89.2","max E-Measure":"94.9","max F-Measure":"90.0"},"uses_additional_data":true,"paper_date":"2020-08-26","paper":"/paper/siamese-network-for-rgb-d-salient-object","paper_url":"https://arxiv.org/abs/2008.12134v2","paper_title":"Siamese Network for RGB-D Salient Object Detection and Beyond","code":"https://github.com/taozh2017/RGBD-SODsurvey","n_code_links":2,"syntology":null},{"rank_in_archive_order":7,"model":"UCNet-CVAE","metrics":{"Average MAE":"0.045","S-Measure":"88.3"},"uses_additional_data":false,"paper_date":"2020-09-07","paper":"/paper/uncertainty-inspired-rgb-d-saliency-detection","paper_url":"https://arxiv.org/abs/2009.03075v1","paper_title":"Uncertainty Inspired RGB-D Saliency Detection","code":"https://github.com/taozh2017/RGBD-SODsurvey","n_code_links":4,"syntology":null},{"rank_in_archive_order":8,"model":"BiANet","metrics":{"Average MAE":"0.052","S-Measure":"88.3","max E-Measure":"92.5","max F-Measure":"89.0"},"uses_additional_data":false,"paper_date":"2020-04-30","paper":"/paper/bilateral-attention-network-for-rgb-d-salient","paper_url":"https://arxiv.org/abs/2004.14582v1","paper_title":"Bilateral Attention Network for RGB-D Salient Object Detection","code":"https://github.com/zzhanghub/bianet","n_code_links":1,"syntology":null},{"rank_in_archive_order":9,"model":"JL-DCF","metrics":{"Average MAE":"0.051","S-Measure":"87.9","max E-Measure":"92.3","max F-Measure":"88.5"},"uses_additional_data":false,"paper_date":"2020-04-18","paper":"/paper/jl-dcf-joint-learning-and-densely-cooperative","paper_url":"https://arxiv.org/abs/2004.08515v1","paper_title":"JL-DCF: Joint Learning and Densely-Cooperative Fusion Framework for RGB-D Salient Object Detection","code":"https://github.com/kerenfu/JLDCF","n_code_links":1,"syntology":null},{"rank_in_archive_order":10,"model":"BBS-Net","metrics":{"Average MAE":"0.055","S-Measure":"87.9","max E-Measure":"92.2","max F-Measure":"88.3"},"uses_additional_data":false,"paper_date":"2020-07-06","paper":"/paper/bbs-net-rgb-d-salient-object-detection-with-a","paper_url":"https://arxiv.org/abs/2007.02713v3","paper_title":"Bifurcated backbone strategy for RGB-D salient object detection","code":"https://github.com/zyjwuyan/BBS-Net","n_code_links":2,"syntology":{"n_ran":3,"n_unverified":2,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":11,"model":"UCNet-ABP","metrics":{"Average MAE":"0.049","S-Measure":"87.6"},"uses_additional_data":false,"paper_date":"2020-09-07","paper":"/paper/uncertainty-inspired-rgb-d-saliency-detection","paper_url":"https://arxiv.org/abs/2009.03075v1","paper_title":"Uncertainty Inspired RGB-D Saliency Detection","code":"https://github.com/taozh2017/RGBD-SODsurvey","n_code_links":4,"syntology":null},{"rank_in_archive_order":12,"model":"UC-Net","metrics":{"Average MAE":"0.051","S-Measure":"87.5"},"uses_additional_data":false,"paper_date":"2020-04-13","paper":"/paper/uc-net-uncertainty-inspired-rgb-d-saliency","paper_url":"https://arxiv.org/abs/2004.05763v1","paper_title":"UC-Net: Uncertainty Inspired RGB-D Saliency Detection via Conditional Variational Autoencoders","code":"https://github.com/JingZhang617/UCNet","n_code_links":1,"syntology":null},{"rank_in_archive_order":13,"model":"PGAR","metrics":{"Average MAE":"0.059","S-Measure":"87.5"},"uses_additional_data":false,"paper_date":"2020-08-17","paper":"/paper/progressively-guided-alternate-refinement","paper_url":"https://arxiv.org/abs/2008.07064v1","paper_title":"Progressively Guided Alternate Refinement Network for RGB-D Salient Object Detection","code":"https://github.com/ShuhanChen/PGAR_ECCV20","n_code_links":1,"syntology":null},{"rank_in_archive_order":14,"model":"D3Net","metrics":{"Average MAE":"0.063","S-Measure":"86.0","max E-Measure":"90.9","max F-Measure":"86.1"},"uses_additional_data":false,"paper_date":"2019-07-15","paper":"/paper/rethinking-rgb-d-salient-object-detection","paper_url":"https://arxiv.org/abs/1907.06781v2","paper_title":"Rethinking RGB-D Salient Object Detection: Models, Data Sets, and Large-Scale Benchmarks","code":"https://github.com/taozh2017/RGBD-SODsurvey","n_code_links":2,"syntology":null},{"rank_in_archive_order":15,"model":"CPFP","metrics":{"Average MAE":"0.064","S-Measure":"85.0","max E-Measure":"90.3","max F-Measure":"85.1"},"uses_additional_data":false,"paper_date":"2019-06-01","paper":"/paper/contrast-prior-and-fluid-pyramid-integration","paper_url":"http://openaccess.thecvf.com/content_CVPR_2019/html/Zhao_Contrast_Prior_and_Fluid_Pyramid_Integration_for_RGBD_Salient_Object_CVPR_2019_paper.html","paper_title":"Contrast Prior and Fluid Pyramid Integration for RGBD Salient Object Detection","code":"https://github.com/taozh2017/RGBD-SODsurvey","n_code_links":2,"syntology":null},{"rank_in_archive_order":16,"model":"DDNet","metrics":{"Average MAE":"0.043"},"uses_additional_data":true,"paper_date":"2021-02-12","paper":"/paper/densely-deformable-efficient-salient-object","paper_url":"https://arxiv.org/abs/2102.06407v1","paper_title":"Densely Deformable Efficient Salient Object Detection Network","code":"https://github.com/tanveer-hussain/EfficientSOD","n_code_links":1,"syntology":null}],"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 7,081 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":7081,"papers_extracted_not_yet_verified":217,"boards_without_verdict":27,"papers_not_yet_extracted":2325},"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":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":20,"n_unverified":10,"n_samples":30,"n_pointer_only_licence":11,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":20,"n_unverified":10,"n_samples":30,"n_pointer_only_licence":11,"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"}}}