{"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/hdc-hierarchical-semantic-decoding-with-1","title":"CoHD: A Counting-Aware Hierarchical Decoding Framework for Generalized Referring Expression Segmentation","arxiv_id":"2405.15658","date":"2024-05-24","proceeding":null,"authors":["Zhuoyan Luo","Yinghao Wu","Tianheng Cheng","Yong liu","Yicheng Xiao","Hongfa Wang","Xiao-Ping Zhang","Yujiu Yang"],"abstract":"The newly proposed Generalized Referring Expression Segmentation (GRES) amplifies the formulation of classic RES by involving complex multiple/non-target scenarios. Recent approaches address GRES by directly extending the well-adopted RES frameworks with object-existence identification. However, these approaches tend to encode multi-granularity object information into a single representation, which makes it difficult to precisely represent comprehensive objects of different granularity. Moreover, the simple binary object-existence identification across all referent scenarios fails to specify their inherent differences, incurring ambiguity in object understanding. To tackle the above issues, we propose a \\textbf{Co}unting-Aware \\textbf{H}ierarchical \\textbf{D}ecoding framework (CoHD) for GRES. By decoupling the intricate referring semantics into different granularity with a visual-linguistic hierarchy, and dynamic aggregating it with intra- and inter-selection, CoHD boosts multi-granularity comprehension with the reciprocal benefit of the hierarchical nature. Furthermore, we incorporate the counting ability by embodying multiple/single/non-target scenarios into count- and category-level supervision, facilitating comprehensive object perception. Experimental results on gRefCOCO, Ref-ZOM, R-RefCOCO, and RefCOCO benchmarks demonstrate the effectiveness and rationality of CoHD which outperforms state-of-the-art GRES methods by a remarkable margin. Code is available at \\href{https://github.com/RobertLuo1/CoHD}{here}.","url_abs":"https://arxiv.org/abs/2405.15658v2","url_pdf":"https://arxiv.org/pdf/2405.15658v2.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":"hdc-hierarchical-semantic-decoding-with-1","repo_url":"https://github.com/RobertLuo1/HDC","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"hdc-hierarchical-semantic-decoding-with-1","repo_url":"https://github.com/robertluo1/cohd","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"generalized-referring-expression-segmentation","task_name":"Generalized Referring Expression Segmentation"},{"task_slug":"object","task_name":"Object"},{"task_slug":"referring-expression","task_name":"Referring Expression"},{"task_slug":"referring-expression-segmentation","task_name":"Referring Expression Segmentation"},{"task_slug":"semantic-correspondence","task_name":"Semantic correspondence"}],"methods":[{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/generalized-referring-expression-segmentation","task":"Generalized Referring Expression Segmentation","dataset":"gRefCOCO","model":"HDC","rank_in_archive_order":4,"of":13,"metrics":{"cIoU":"65.42","gIoU":"68.28"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2405.15658","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}