{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/highly-accurate-dichotomous-image","title":"Highly Accurate Dichotomous Image Segmentation","arxiv_id":"2203.03041","date":"2022-03-06","proceeding":null,"authors":["Xuebin Qin","Hang Dai","Xiaobin Hu","Deng-Ping Fan","Ling Shao","and Luc Van Gool"],"abstract":"We present a systematic study on a new task called dichotomous image segmentation (DIS) , which aims to segment highly accurate objects from natural images. To this end, we collected the first large-scale DIS dataset, called DIS5K, which contains 5,470 high-resolution (e.g., 2K, 4K or larger) images covering camouflaged, salient, or meticulous objects in various backgrounds. DIS is annotated with extremely fine-grained labels. Besides, we introduce a simple intermediate supervision baseline (IS-Net) using both feature-level and mask-level guidance for DIS model training. IS-Net outperforms various cutting-edge baselines on the proposed DIS5K, making it a general self-learned supervision network that can facilitate future research in DIS. Further, we design a new metric called human correction efforts (HCE) which approximates the number of mouse clicking operations required to correct the false positives and false negatives. HCE is utilized to measure the gap between models and real-world applications and thus can complement existing metrics. Finally, we conduct the largest-scale benchmark, evaluating 16 representative segmentation models, providing a more insightful discussion regarding object complexities, and showing several potential applications (e.g., background removal, art design, 3D reconstruction). Hoping these efforts can open up promising directions for both academic and industries. Project page: https://xuebinqin.github.io/dis/index.html.","url_abs":"https://arxiv.org/abs/2203.03041v4","url_pdf":"https://arxiv.org/pdf/2203.03041v4.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"highly-accurate-dichotomous-image","repo_url":"https://github.com/xuebinqin/DIS","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"2k","task_name":"2k"},{"task_slug":"3d-reconstruction","task_name":"3D Reconstruction"},{"task_slug":"4k","task_name":"4k"},{"task_slug":"dichotomous-image-segmentation","task_name":"Dichotomous Image Segmentation"},{"task_slug":"image-segmentation","task_name":"Image Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[{"slug":"dis5k","name":"DIS5K","full_name":"Dichotomous Image Segmentation (DIS) Dataset"}],"methods_introduced":[],"results":[{"leaderboard":"/sota/dichotomous-image-segmentation-on-dis-te1","task":"Dichotomous Image Segmentation","dataset":"DIS-TE1","model":"IS-Net","rank_in_archive_order":6,"of":22,"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},{"leaderboard":"/sota/dichotomous-image-segmentation-on-dis-te2","task":"Dichotomous Image Segmentation","dataset":"DIS-TE2","model":"IS-Net","rank_in_archive_order":6,"of":22,"metrics":{"E-measure":"0.858","HCE":"340","MAE":"0.07","S-Measure":"0.823","max F-Measure":"0.799","weighted F-measure":"0.728"},"uses_additional_data":false},{"leaderboard":"/sota/dichotomous-image-segmentation-on-dis-te3","task":"Dichotomous Image Segmentation","dataset":"DIS-TE3","model":"IS-Net","rank_in_archive_order":6,"of":22,"metrics":{"E-measure":"0.883","HCE":"687","MAE":"0.064","S-Measure":"0.836","max F-Measure":"0.830","weighted F-measure":"0.758"},"uses_additional_data":false},{"leaderboard":"/sota/dichotomous-image-segmentation-on-dis-te4","task":"Dichotomous Image Segmentation","dataset":"DIS-TE4","model":"IS-Net","rank_in_archive_order":6,"of":22,"metrics":{"E-measure":"0.87","HCE":"2888","MAE":"0.072","S-Measure":"0.83","max F-Measure":"0.827","weighted F-measure":"0.753"},"uses_additional_data":false},{"leaderboard":"/sota/dichotomous-image-segmentation-on-dis-vd","task":"Dichotomous Image Segmentation","dataset":"DIS-VD","model":"IS-Net","rank_in_archive_order":8,"of":24,"metrics":{"E-measure":"0.856","HCE":"1116","MAE":"0.074","S-Measure":"0.813","max F-Measure":"0.791","weighted F-measure":"0.717"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2203.03041","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.03041"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/xuebinqin/DIS","reach":null}],"summary":{"ran":6,"ran_fixture":3,"unverified":1},"by_repo_kind":{"official":{"samples":10,"ran":9,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"afa31b2882bc3c34","entry":"REBNCONV","repo":"xuebinqin/DIS","repo_kind":"official","path":"IS-Net/models/isnet.py","file_url":"https://github.com/xuebinqin/DIS/blob/HEAD/IS-Net/models/isnet.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"afa31b2882bc3c34"}},{"code_sha256_prefix":"02cc50421ae7b439","entry":"RSU4","repo":"xuebinqin/DIS","repo_kind":"official","path":"IS-Net/models/isnet.py","file_url":"https://github.com/xuebinqin/DIS/blob/HEAD/IS-Net/models/isnet.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"02cc50421ae7b439"}},{"code_sha256_prefix":"b61cd5f9e93344c3","entry":"RSU4F","repo":"xuebinqin/DIS","repo_kind":"official","path":"IS-Net/models/isnet.py","file_url":"https://github.com/xuebinqin/DIS/blob/HEAD/IS-Net/models/isnet.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b61cd5f9e93344c3"}},{"code_sha256_prefix":"4e74b24c0513bd83","entry":"RSU5","repo":"xuebinqin/DIS","repo_kind":"official","path":"IS-Net/models/isnet.py","file_url":"https://github.com/xuebinqin/DIS/blob/HEAD/IS-Net/models/isnet.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4e74b24c0513bd83"}},{"code_sha256_prefix":"dec5dbb951aa5aa8","entry":"RSU6","repo":"xuebinqin/DIS","repo_kind":"official","path":"IS-Net/models/isnet.py","file_url":"https://github.com/xuebinqin/DIS/blob/HEAD/IS-Net/models/isnet.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"dec5dbb951aa5aa8"}},{"code_sha256_prefix":"5f39ebc09fa09f33","entry":"RSU7","repo":"xuebinqin/DIS","repo_kind":"official","path":"IS-Net/models/isnet.py","file_url":"https://github.com/xuebinqin/DIS/blob/HEAD/IS-Net/models/isnet.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5f39ebc09fa09f33"}},{"code_sha256_prefix":"bfdbf21066b9aaf1","entry":"_upsample_like","repo":"xuebinqin/DIS","repo_kind":"official","path":"IS-Net/models/isnet.py","file_url":"https://github.com/xuebinqin/DIS/blob/HEAD/IS-Net/models/isnet.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"bfdbf21066b9aaf1"}},{"code_sha256_prefix":"2ca2e4925d3db933","entry":"muti_loss_fusion","repo":"xuebinqin/DIS","repo_kind":"official","path":"IS-Net/models/isnet.py","file_url":"https://github.com/xuebinqin/DIS/blob/HEAD/IS-Net/models/isnet.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2ca2e4925d3db933"}},{"code_sha256_prefix":"f8c4571c67857327","entry":"muti_loss_fusion_kl","repo":"xuebinqin/DIS","repo_kind":"official","path":"IS-Net/models/isnet.py","file_url":"https://github.com/xuebinqin/DIS/blob/HEAD/IS-Net/models/isnet.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f8c4571c67857327"}},{"code_sha256_prefix":"67b132694943823c","entry":"ISNetDIS","repo":"xuebinqin/DIS","repo_kind":"official","path":"IS-Net/models/isnet.py","file_url":"https://github.com/xuebinqin/DIS/blob/HEAD/IS-Net/models/isnet.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"67b132694943823c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}