{"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/gres-generalized-referring-expression-1","title":"GRES: Generalized Referring Expression Segmentation","arxiv_id":"2306.00968","date":"2023-06-01","proceeding":"CVPR 2023 1","authors":["Chang Liu","Henghui Ding","Xudong Jiang"],"abstract":"Referring Expression Segmentation (RES) aims to generate a segmentation mask for the object described by a given language expression. Existing classic RES datasets and methods commonly support single-target expressions only, i.e., one expression refers to one target object. Multi-target and no-target expressions are not considered. This limits the usage of RES in practice. In this paper, we introduce a new benchmark called Generalized Referring Expression Segmentation (GRES), which extends the classic RES to allow expressions to refer to an arbitrary number of target objects. Towards this, we construct the first large-scale GRES dataset called gRefCOCO that contains multi-target, no-target, and single-target expressions. GRES and gRefCOCO are designed to be well-compatible with RES, facilitating extensive experiments to study the performance gap of the existing RES methods on the GRES task. In the experimental study, we find that one of the big challenges of GRES is complex relationship modeling. Based on this, we propose a region-based GRES baseline ReLA that adaptively divides the image into regions with sub-instance clues, and explicitly models the region-region and region-language dependencies. The proposed approach ReLA achieves new state-of-the-art performance on the both newly proposed GRES and classic RES tasks. The proposed gRefCOCO dataset and method are available at https://henghuiding.github.io/GRES.","url_abs":"https://arxiv.org/abs/2306.00968v1","url_pdf":"https://arxiv.org/pdf/2306.00968v1.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":"gres-generalized-referring-expression-1","repo_url":"https://github.com/henghuiding/ReLA","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"gres-generalized-referring-expression-1","repo_url":"https://github.com/henghuiding/grefcoco","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"generalized-referring-expression-segmentation","task_name":"Generalized Referring Expression Segmentation"},{"task_slug":"referring-expression","task_name":"Referring Expression"},{"task_slug":"referring-expression-segmentation","task_name":"Referring Expression Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/generalized-referring-expression-segmentation","task":"Generalized Referring Expression Segmentation","dataset":"gRefCOCO","model":"ReLA","rank_in_archive_order":8,"of":13,"metrics":{"cIoU":"62.42","gIoU":"63.60"},"uses_additional_data":false},{"leaderboard":"/sota/referring-expression-segmentation-on-refcoco-5","task":"Referring Expression Segmentation","dataset":"RefCOCO+ test B","model":"ReLA","rank_in_archive_order":16,"of":30,"metrics":{"Overall IoU":"57.65"},"uses_additional_data":false},{"leaderboard":"/sota/referring-expression-segmentation-on-refcoco-4","task":"Referring Expression Segmentation","dataset":"RefCOCO+ testA","model":"ReLA","rank_in_archive_order":17,"of":30,"metrics":{"Overall IoU":"71.02"},"uses_additional_data":false},{"leaderboard":"/sota/referring-expression-segmentation-on-refcoco-3","task":"Referring Expression Segmentation","dataset":"RefCOCO+ val","model":"ReLA","rank_in_archive_order":20,"of":33,"metrics":{"Overall IoU":"66.04"},"uses_additional_data":false},{"leaderboard":"/sota/referring-expression-segmentation-on-refcoco","task":"Referring Expression Segmentation","dataset":"RefCoCo val","model":"ReLA","rank_in_archive_order":20,"of":37,"metrics":{"Overall IoU":"73.82"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2306.00968","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.00968"}},"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/henghuiding/grefcoco","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/henghuiding/ReLA","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_fixture":1,"ran_draft_wrong":1,"unverified":3},"by_repo_kind":{"official":{"samples":5,"ran":2,"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":"144d10b49baeb8a6","entry":"window_partition","repo":"henghuiding/ReLA","repo_kind":"official","path":"gres_model/modeling/backbone/swin.py","file_url":"https://github.com/henghuiding/ReLA/blob/HEAD/gres_model/modeling/backbone/swin.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":2,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"144d10b49baeb8a6"}},{"code_sha256_prefix":"61bf152e6a42a184","entry":"window_reverse","repo":"henghuiding/ReLA","repo_kind":"official","path":"gres_model/modeling/backbone/swin.py","file_url":"https://github.com/henghuiding/ReLA/blob/HEAD/gres_model/modeling/backbone/swin.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"61bf152e6a42a184"}},{"code_sha256_prefix":"745bf09fefeb50c3","entry":"computeIoU","repo":"henghuiding/ReLA","repo_kind":"official","path":"gres_model/evaluation/refer_evaluation.py","file_url":"https://github.com/henghuiding/ReLA/blob/HEAD/gres_model/evaluation/refer_evaluation.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"745bf09fefeb50c3"}},{"code_sha256_prefix":"58cc9ff3bf75e753","entry":"nested_tensor_from_tensor_list","repo":"henghuiding/ReLA","repo_kind":"official","path":"gres_model/utils/misc.py","file_url":"https://github.com/henghuiding/ReLA/blob/HEAD/gres_model/utils/misc.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"58cc9ff3bf75e753"}},{"code_sha256_prefix":"7a65189d5697386f","entry":"refer_ce_loss","repo":"henghuiding/ReLA","repo_kind":"official","path":"gres_model/modeling/criterion.py","file_url":"https://github.com/henghuiding/ReLA/blob/HEAD/gres_model/modeling/criterion.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7a65189d5697386f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}