{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/focus-towards-universal-foreground","title":"FOCUS: Towards Universal Foreground Segmentation","arxiv_id":"2501.05238","date":"2025-01-09","proceeding":null,"authors":["Zuyao You","Lingyu Kong","Lingchen Meng","Zuxuan Wu"],"abstract":"Foreground segmentation is a fundamental task in computer vision, encompassing various subdivision tasks. Previous research has typically designed task-specific architectures for each task, leading to a lack of unification. Moreover, they primarily focus on recognizing foreground objects without effectively distinguishing them from the background. In this paper, we emphasize the importance of the background and its relationship with the foreground. We introduce FOCUS, the Foreground ObjeCts Universal Segmentation framework that can handle multiple foreground tasks. We develop a multi-scale semantic network using the edge information of objects to enhance image features. To achieve boundary-aware segmentation, we propose a novel distillation method, integrating the contrastive learning strategy to refine the prediction mask in multi-modal feature space. We conduct extensive experiments on a total of 13 datasets across 5 tasks, and the results demonstrate that FOCUS consistently outperforms the state-of-the-art task-specific models on most metrics.","url_abs":"https://arxiv.org/abs/2501.05238v1","url_pdf":"https://arxiv.org/pdf/2501.05238v1.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":"focus-towards-universal-foreground","repo_url":"https://github.com/geshang777/FOCUS","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"camouflaged-object-segmentation","task_name":"Camouflaged Object Segmentation"},{"task_slug":"defocus-blur-detection","task_name":"Defocus Blur Detection"},{"task_slug":"foreground-segmentation","task_name":"Foreground Segmentation"},{"task_slug":"salient-object-detection-1","task_name":"Salient Object Detection"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"universal-segmentation","task_name":"Universal Segmentation"}],"methods":[{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"},{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/camouflaged-object-segmentation-on-camo","task":"Camouflaged Object Segmentation","dataset":"CAMO","model":"FOCUS","rank_in_archive_order":1,"of":14,"metrics":{"MAE":"0.025","S-Measure":"0.912","Weighted F-Measure":"0.904"},"uses_additional_data":false},{"leaderboard":"/sota/camouflaged-object-segmentation-on-chameleon","task":"Camouflaged Object Segmentation","dataset":"CHAMELEON","model":"FOCUS","rank_in_archive_order":4,"of":6,"metrics":{"MAE":"0.017","S-measure":"0.922","weighted F-measure":"0.908"},"uses_additional_data":false},{"leaderboard":"/sota/camouflaged-object-segmentation-on-cod","task":"Camouflaged Object Segmentation","dataset":"COD","model":"FOCUS","rank_in_archive_order":2,"of":12,"metrics":{"MAE":"0.013","S-Measure":"0.910","Weighted F-Measure":"0.883"},"uses_additional_data":false},{"leaderboard":"/sota/camouflaged-object-segmentation-on-nc4k","task":"Camouflaged Object Segmentation","dataset":"NC4K","model":"FOCUS","rank_in_archive_order":1,"of":6,"metrics":{"MAE":"0.020","S-measure":"0.915","weighted F-measure":"0.906"},"uses_additional_data":false},{"leaderboard":"/sota/salient-object-detection-on-dut-omron-2","task":"Salient Object Detection","dataset":"DUT-OMRON","model":"FOCUS","rank_in_archive_order":2,"of":8,"metrics":{"E-measure":"0.900","MAE":"0.045","S-measure":"0.868"},"uses_additional_data":false},{"leaderboard":"/sota/salient-object-detection-on-duts-te-1","task":"Salient Object Detection","dataset":"DUTS-TE","model":"FOCUS","rank_in_archive_order":2,"of":8,"metrics":{"E-measure":"0.965","MAE":"0.019","Smeasure":"0.929"},"uses_additional_data":false},{"leaderboard":"/sota/salient-object-detection-on-ecssd-1","task":"Salient Object Detection","dataset":"ECSSD","model":"FOCUS","rank_in_archive_order":2,"of":10,"metrics":{"E-measure":"0.971","MAE":"0.018","S-measure":"0.943"},"uses_additional_data":false},{"leaderboard":"/sota/salient-object-detection-on-hku-is-1","task":"Salient Object Detection","dataset":"HKU-IS","model":"FOCUS","rank_in_archive_order":2,"of":9,"metrics":{"E-measure":"0.974","MAE":"0.018","S-measure":"0.935"},"uses_additional_data":false},{"leaderboard":"/sota/salient-object-detection-on-pascal-s-1","task":"Salient Object Detection","dataset":"PASCAL-S","model":"FOCUS","rank_in_archive_order":1,"of":10,"metrics":{"E-measure":"0.942","MAE":"0.036","S-measure":"0.898"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2501.05238","atlas_url":"https://app.syntology.ai/?focus=2501.05238","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2501.05238"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2501.05238\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2501.05238"},"call":"get_concepts_for_paper(arxiv_id=\"2501.05238\")"}],"by_repo":[{"repo":"geshang777/FOCUS","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2506.22624"],"harvested_for_calls":[{"arxiv_id":"2506.22624","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2506.22624"},"call":"get_harvested_code_for_paper(arxiv_id=\"2506.22624\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"64a76575715f9827953ca9a5029a711c555a38c174573e0809ff1d2d28699c66","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}