{"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/going-denser-with-open-vocabulary-part","title":"Going Denser with Open-Vocabulary Part Segmentation","arxiv_id":"2305.11173","date":"2023-05-18","proceeding":"ICCV 2023 1","authors":["Peize Sun","Shoufa Chen","Chenchen Zhu","Fanyi Xiao","Ping Luo","Saining Xie","Zhicheng Yan"],"abstract":"Object detection has been expanded from a limited number of categories to open vocabulary. Moving forward, a complete intelligent vision system requires understanding more fine-grained object descriptions, object parts. In this paper, we propose a detector with the ability to predict both open-vocabulary objects and their part segmentation. This ability comes from two designs. First, we train the detector on the joint of part-level, object-level and image-level data to build the multi-granularity alignment between language and image. Second, we parse the novel object into its parts by its dense semantic correspondence with the base object. These two designs enable the detector to largely benefit from various data sources and foundation models. In open-vocabulary part segmentation experiments, our method outperforms the baseline by 3.3$\\sim$7.3 mAP in cross-dataset generalization on PartImageNet, and improves the baseline by 7.3 novel AP$_{50}$ in cross-category generalization on Pascal Part. Finally, we train a detector that generalizes to a wide range of part segmentation datasets while achieving better performance than dataset-specific training.","url_abs":"https://arxiv.org/abs/2305.11173v1","url_pdf":"https://arxiv.org/pdf/2305.11173v1.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":"going-denser-with-open-vocabulary-part","repo_url":"https://github.com/facebookresearch/vlpart","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"going-denser-with-open-vocabulary-part","repo_url":"https://github.com/cheems-seminar/grounded-segment-any-parts","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-correspondence","task_name":"Semantic correspondence"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"base","method_name":"BASE"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2305.11173","atlas_url":"https://app.syntology.ai/?focus=2305.11173","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.11173"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/cheems-seminar/grounded-segment-any-parts","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/facebookresearch/vlpart","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":5,"samples":[{"code_sha256_prefix":"f9fd6241d935f07b","entry":"window_partition","repo":"facebookresearch/vlpart","repo_kind":"official","path":"vlpart/modeling/backbone/swintransformer.py","file_url":"https://github.com/facebookresearch/vlpart/blob/HEAD/vlpart/modeling/backbone/swintransformer.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"f9fd6241d935f07b"}},{"code_sha256_prefix":"fb32094c6dbece71","entry":"window_reverse","repo":"facebookresearch/vlpart","repo_kind":"official","path":"vlpart/modeling/backbone/swintransformer.py","file_url":"https://github.com/facebookresearch/vlpart/blob/HEAD/vlpart/modeling/backbone/swintransformer.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":false,"mcp_get_code":{"code_sha256":"fb32094c6dbece71"}},{"code_sha256_prefix":"1f97465a9cdcc617","entry":"center_of_mass","repo":"facebookresearch/vlpart","repo_kind":"official","path":"vlpart/modeling/meta_arch/parser_net_mixer.py","file_url":"https://github.com/facebookresearch/vlpart/blob/HEAD/vlpart/modeling/meta_arch/parser_net_mixer.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":false,"mcp_get_code":{"code_sha256":"1f97465a9cdcc617"}},{"code_sha256_prefix":"a11a4946af0a8f49","entry":"chunk_cosine_sim","repo":"facebookresearch/vlpart","repo_kind":"official","path":"vlpart/modeling/meta_arch/parser_net_mixer.py","file_url":"https://github.com/facebookresearch/vlpart/blob/HEAD/vlpart/modeling/meta_arch/parser_net_mixer.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":false,"mcp_get_code":{"code_sha256":"a11a4946af0a8f49"}},{"code_sha256_prefix":"3634f2208a0255d7","entry":"create_timm_resnet","repo":"facebookresearch/vlpart","repo_kind":"official","path":"vlpart/modeling/backbone/timm.py","file_url":"https://github.com/facebookresearch/vlpart/blob/HEAD/vlpart/modeling/backbone/timm.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":false,"mcp_get_code":{"code_sha256":"3634f2208a0255d7"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}