{"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/codet-co-occurrence-guided-region-word-1","title":"CoDet: Co-Occurrence Guided Region-Word Alignment for Open-Vocabulary Object Detection","arxiv_id":"2310.16667","date":"2023-10-25","proceeding":"NeurIPS 2023 11","authors":["Chuofan Ma","Yi Jiang","Xin Wen","Zehuan Yuan","Xiaojuan Qi"],"abstract":"Deriving reliable region-word alignment from image-text pairs is critical to learn object-level vision-language representations for open-vocabulary object detection. Existing methods typically rely on pre-trained or self-trained vision-language models for alignment, which are prone to limitations in localization accuracy or generalization capabilities. In this paper, we propose CoDet, a novel approach that overcomes the reliance on pre-aligned vision-language space by reformulating region-word alignment as a co-occurring object discovery problem. Intuitively, by grouping images that mention a shared concept in their captions, objects corresponding to the shared concept shall exhibit high co-occurrence among the group. CoDet then leverages visual similarities to discover the co-occurring objects and align them with the shared concept. Extensive experiments demonstrate that CoDet has superior performances and compelling scalability in open-vocabulary detection, e.g., by scaling up the visual backbone, CoDet achieves 37.0 $\\text{AP}^m_{novel}$ and 44.7 $\\text{AP}^m_{all}$ on OV-LVIS, surpassing the previous SoTA by 4.2 $\\text{AP}^m_{novel}$ and 9.8 $\\text{AP}^m_{all}$. Code is available at https://github.com/CVMI-Lab/CoDet.","url_abs":"https://arxiv.org/abs/2310.16667v1","url_pdf":"https://arxiv.org/pdf/2310.16667v1.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":"codet-co-occurrence-guided-region-word-1","repo_url":"https://github.com/cvmi-lab/codet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-discovery","task_name":"Object Discovery"},{"task_slug":"open-vocabulary-object-detection","task_name":"Open Vocabulary Object Detection"},{"task_slug":"open-vocabulary-object-detection","task_name":"Open-vocabulary object detection"},{"task_slug":"word-alignment","task_name":"Word Alignment"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"align","method_name":"ALIGN"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/open-vocabulary-object-detection-on-lvis-v1-0","task":"Open Vocabulary Object Detection","dataset":"LVIS v1.0","model":"CoDet (EVA02-L)","rank_in_archive_order":4,"of":28,"metrics":{"AP novel-LVIS base training":"37.0"},"uses_additional_data":true}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2310.16667","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.16667"}},"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":"deterministic:regex_extraction","url":"https://github.com/CVMI-Lab/CoDet","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/cvmi-lab/codet","reach":{"status":"ok"}}],"summary":{"ran":3,"ran_violates":1,"ran_fixture":1,"ran_draft_wrong":1,"unverified":2},"by_repo_kind":{"official":{"samples":8,"ran":6,"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":8,"samples":[{"code_sha256_prefix":"2da304dcdb0e104d","entry":"get_clip_embeddings","repo":"CVMI-Lab/CoDet","repo_kind":"official","path":"codet/predictor.py","file_url":"https://github.com/CVMI-Lab/CoDet/blob/HEAD/codet/predictor.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2da304dcdb0e104d"}},{"code_sha256_prefix":"bb583e07209fe58b","entry":"get_fed_loss_inds","repo":"CVMI-Lab/CoDet","repo_kind":"official","path":"codet/modeling/utils.py","file_url":"https://github.com/CVMI-Lab/CoDet/blob/HEAD/codet/modeling/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"bb583e07209fe58b"}},{"code_sha256_prefix":"1f6e4c3da7b82979","entry":"load_class_freq","repo":"CVMI-Lab/CoDet","repo_kind":"official","path":"codet/modeling/utils.py","file_url":"https://github.com/CVMI-Lab/CoDet/blob/HEAD/codet/modeling/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1f6e4c3da7b82979"}},{"code_sha256_prefix":"c15434906f804d7f","entry":"match_name_keywords","repo":"CVMI-Lab/CoDet","repo_kind":"official","path":"codet/custom_solver.py","file_url":"https://github.com/CVMI-Lab/CoDet/blob/HEAD/codet/custom_solver.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c15434906f804d7f"}},{"code_sha256_prefix":"f9fd6241d935f07b","entry":"window_partition","repo":"CVMI-Lab/CoDet","repo_kind":"official","path":"codet/modeling/backbone/swintransformer.py","file_url":"https://github.com/CVMI-Lab/CoDet/blob/HEAD/codet/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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f9fd6241d935f07b"}},{"code_sha256_prefix":"fb32094c6dbece71","entry":"window_reverse","repo":"CVMI-Lab/CoDet","repo_kind":"official","path":"codet/modeling/backbone/swintransformer.py","file_url":"https://github.com/CVMI-Lab/CoDet/blob/HEAD/codet/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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"fb32094c6dbece71"}},{"code_sha256_prefix":"2e0a799ccbd489e7","entry":"compute_average_precision","repo":"CVMI-Lab/CoDet","repo_kind":"official","path":"codet/evaluation/oideval.py","file_url":"https://github.com/CVMI-Lab/CoDet/blob/HEAD/codet/evaluation/oideval.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2e0a799ccbd489e7"}},{"code_sha256_prefix":"3634f2208a0255d7","entry":"create_timm_resnet","repo":"CVMI-Lab/CoDet","repo_kind":"official","path":"codet/modeling/backbone/timm.py","file_url":"https://github.com/CVMI-Lab/CoDet/blob/HEAD/codet/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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3634f2208a0255d7"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}