{"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/open-vocabulary-object-detection-with","title":"Open Vocabulary Object Detection with Proposal Mining and Prediction Equalization","arxiv_id":"2206.11134","date":"2022-06-22","proceeding":null,"authors":["Peixian Chen","Kekai Sheng","Mengdan Zhang","Mingbao Lin","Yunhang Shen","Shaohui Lin","Bo Ren","Ke Li"],"abstract":"Open-vocabulary object detection (OVD) aims to scale up vocabulary size to detect objects of novel categories beyond the training vocabulary. Recent work resorts to the rich knowledge in pre-trained vision-language models. However, existing methods are ineffective in proposal-level vision-language alignment. Meanwhile, the models usually suffer from confidence bias toward base categories and perform worse on novel ones. To overcome the challenges, we present MEDet, a novel and effective OVD framework with proposal mining and prediction equalization. First, we design an online proposal mining to refine the inherited vision-semantic knowledge from coarse to fine, allowing for proposal-level detection-oriented feature alignment. Second, based on causal inference theory, we introduce a class-wise backdoor adjustment to reinforce the predictions on novel categories to improve the overall OVD performance. Extensive experiments on COCO and LVIS benchmarks verify the superiority of MEDet over the competing approaches in detecting objects of novel categories, e.g., 32.6% AP50 on COCO and 22.4% mask mAP on LVIS.","url_abs":"https://arxiv.org/abs/2206.11134v4","url_pdf":"https://arxiv.org/pdf/2206.11134v4.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":"open-vocabulary-object-detection-with","repo_url":"https://github.com/pealing/medet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"open-vocabulary-object-detection-with","repo_url":"https://github.com/peixianchen/medet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"causal-inference","task_name":"Causal Inference"},{"task_slug":"object-detection","task_name":"Object Detection"},{"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":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"base","method_name":"BASE"}],"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":"MEDet","rank_in_archive_order":18,"of":28,"metrics":{"AP novel-LVIS base training":"22.4"},"uses_additional_data":false},{"leaderboard":"/sota/open-vocabulary-object-detection-on-mscoco","task":"Open Vocabulary Object Detection","dataset":"MSCOCO","model":"MEDet (RN50)","rank_in_archive_order":22,"of":32,"metrics":{"AP 0.5":" 32.6"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2206.11134","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.11134"}},"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/peixianchen/medet","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/pealing/medet","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":3,"ran_violates":1,"ran_fixture":2,"ran_draft_wrong":1,"unverified":2},"by_repo_kind":{"official":{"samples":9,"ran":7,"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":"1f211df98dc51cee","entry":"get_clip_embeddings","repo":"pealing/medet","repo_kind":"official","path":"medet/predictor.py","file_url":"https://github.com/pealing/medet/blob/HEAD/medet/predictor.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1f211df98dc51cee"}},{"code_sha256_prefix":"bb583e07209fe58b","entry":"get_fed_loss_inds","repo":"pealing/medet","repo_kind":"official","path":"medet/modeling/utils.py","file_url":"https://github.com/pealing/medet/blob/HEAD/medet/modeling/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"bb583e07209fe58b"}},{"code_sha256_prefix":"1f6e4c3da7b82979","entry":"load_class_freq","repo":"pealing/medet","repo_kind":"official","path":"medet/modeling/utils.py","file_url":"https://github.com/pealing/medet/blob/HEAD/medet/modeling/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1f6e4c3da7b82979"}},{"code_sha256_prefix":"c15434906f804d7f","entry":"match_name_keywords","repo":"pealing/medet","repo_kind":"official","path":"medet/custom_solver.py","file_url":"https://github.com/pealing/medet/blob/HEAD/medet/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":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c15434906f804d7f"}},{"code_sha256_prefix":"573ab018aa3f2e6f","entry":"permute_to_N_HWA_K","repo":"pealing/medet","repo_kind":"official","path":"medet/modeling/meta_arch/dense_detector.py","file_url":"https://github.com/pealing/medet/blob/HEAD/medet/modeling/meta_arch/dense_detector.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"573ab018aa3f2e6f"}},{"code_sha256_prefix":"f9fd6241d935f07b","entry":"window_partition","repo":"pealing/medet","repo_kind":"official","path":"medet/modeling/backbone/swintransformer.py","file_url":"https://github.com/pealing/medet/blob/HEAD/medet/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":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f9fd6241d935f07b"}},{"code_sha256_prefix":"fb32094c6dbece71","entry":"window_reverse","repo":"pealing/medet","repo_kind":"official","path":"medet/modeling/backbone/swintransformer.py","file_url":"https://github.com/pealing/medet/blob/HEAD/medet/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":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"fb32094c6dbece71"}},{"code_sha256_prefix":"2e0a799ccbd489e7","entry":"compute_average_precision","repo":"pealing/medet","repo_kind":"official","path":"medet/evaluation/oideval.py","file_url":"https://github.com/pealing/medet/blob/HEAD/medet/evaluation/oideval.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2e0a799ccbd489e7"}},{"code_sha256_prefix":"625ac447e2e8b2bc","entry":"create_timm_resnet","repo":"pealing/medet","repo_kind":"official","path":"medet/modeling/backbone/timm.py","file_url":"https://github.com/pealing/medet/blob/HEAD/medet/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":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"625ac447e2e8b2bc"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}