{"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/deris-decoupling-perception-and-cognition-for","title":"DeRIS: Decoupling Perception and Cognition for Enhanced Referring Image Segmentation through Loopback Synergy","arxiv_id":"2507.01738","date":"2025-07-02","proceeding":null,"authors":["Ming Dai","Wenxuan Cheng","Jiang-Jiang Liu","Sen yang","Wenxiao Cai","Yanpeng Sun","Wankou Yang"],"abstract":"Referring Image Segmentation (RIS) is a challenging task that aims to segment objects in an image based on natural language expressions. While prior studies have predominantly concentrated on improving vision-language interactions and achieving fine-grained localization, a systematic analysis of the fundamental bottlenecks in existing RIS frameworks remains underexplored. To bridge this gap, we propose DeRIS, a novel framework that decomposes RIS into two key components: perception and cognition. This modular decomposition facilitates a systematic analysis of the primary bottlenecks impeding RIS performance. Our findings reveal that the predominant limitation lies not in perceptual deficiencies, but in the insufficient multi-modal cognitive capacity of current models. To mitigate this, we propose a Loopback Synergy mechanism, which enhances the synergy between the perception and cognition modules, thereby enabling precise segmentation while simultaneously improving robust image-text comprehension. Additionally, we analyze and introduce a simple non-referent sample conversion data augmentation to address the long-tail distribution issue related to target existence judgement in general scenarios. Notably, DeRIS demonstrates inherent adaptability to both non- and multi-referents scenarios without requiring specialized architectural modifications, enhancing its general applicability. The codes and models are available at https://github.com/Dmmm1997/DeRIS.","url_abs":"https://arxiv.org/abs/2507.01738v1","url_pdf":"https://arxiv.org/pdf/2507.01738v1.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":"deris-decoupling-perception-and-cognition-for","repo_url":"https://github.com/Dmmm1997/DeRIS","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"generalized-referring-expression-segmentation","task_name":"Generalized Referring Expression Segmentation"},{"task_slug":"image-segmentation","task_name":"Image Segmentation"},{"task_slug":"reading-comprehension","task_name":"Reading Comprehension"},{"task_slug":"referring-expression-segmentation","task_name":"Referring Expression Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/generalized-referring-expression-segmentation","task":"Generalized Referring Expression Segmentation","dataset":"gRefCOCO","model":"DeRIS-L","rank_in_archive_order":1,"of":13,"metrics":{"cIoU":"72.00","gIoU":"77.67"},"uses_additional_data":false},{"leaderboard":"/sota/referring-expression-segmentation-on-refcoco-8","task":"Referring Expression Segmentation","dataset":"RefCOCO testA","model":"DeRIS-L","rank_in_archive_order":1,"of":13,"metrics":{"Mean IoU":"86.64","Overall IoU":"86.49"},"uses_additional_data":false},{"leaderboard":"/sota/referring-expression-segmentation-on-refcoco-9","task":"Referring Expression Segmentation","dataset":"RefCOCO testB","model":"DeRIS-L","rank_in_archive_order":2,"of":13,"metrics":{"Mean IoU":"84.52","Overall IoU":"82.87"},"uses_additional_data":false},{"leaderboard":"/sota/referring-expression-segmentation-on-refcoco-5","task":"Referring Expression Segmentation","dataset":"RefCOCO+ test B","model":"DeRIS-L","rank_in_archive_order":29,"of":30,"metrics":{"Mean IoU":"78.59"},"uses_additional_data":false},{"leaderboard":"/sota/referring-expression-segmentation-on-refcoco-4","task":"Referring Expression Segmentation","dataset":"RefCOCO+ testA","model":"DeRIS-L","rank_in_archive_order":3,"of":30,"metrics":{"Mean IoU":"83.74","Overall IoU":"82.34"},"uses_additional_data":false},{"leaderboard":"/sota/referring-expression-segmentation-on-refcoco-3","task":"Referring Expression Segmentation","dataset":"RefCOCO+ val","model":"DeRIS-L","rank_in_archive_order":2,"of":33,"metrics":{"Mean IoU":"81.28","Overall IoU":"79.01"},"uses_additional_data":false},{"leaderboard":"/sota/referring-expression-segmentation-on-refcocog-1","task":"Referring Expression Segmentation","dataset":"RefCOCOg-test","model":"DeRIS-L","rank_in_archive_order":17,"of":18,"metrics":{"Mean IoU":"81.32"},"uses_additional_data":false},{"leaderboard":"/sota/referring-expression-segmentation-on-refcocog","task":"Referring Expression Segmentation","dataset":"RefCOCOg-val","model":"DeRIS-L","rank_in_archive_order":22,"of":23,"metrics":{"Mean IoU":"80.01"},"uses_additional_data":false},{"leaderboard":"/sota/referring-expression-segmentation-on-refcoco","task":"Referring Expression Segmentation","dataset":"RefCoCo val","model":"DeRIS-L","rank_in_archive_order":1,"of":37,"metrics":{"Mean IoU":"85.72","Overall IoU":"85.41"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2507.01738","atlas_url":"https://app.syntology.ai/?focus=2507.01738","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":"2507.01738"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2507.01738\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2507.01738"},"call":"get_concepts_for_paper(arxiv_id=\"2507.01738\")"}],"by_repo":[{"repo":"Dmmm1997/DeRIS","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"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":"b643a5e0a7d121892506a8aca7582b0d0c21034e379ac31ed2f840b8f80b4777","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}