{"url":"/sota/open-vocabulary-object-detection-on-mscoco","task":{"name":"Open Vocabulary Object Detection","url":"/task/open-vocabulary-object-detection","note":null},"dataset":{"name":"MSCOCO","url":"/dataset/mscoco"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"Open-vocabulary detection (OVD) aims to generalize beyond the limited number of base classes labeled during the training phase. The goal is to detect novel classes defined by an unbounded\r\n(open) vocabulary at inference.","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["AP 0.5"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"AP 0.5":"higher"}},"counts":{"rows":32,"rows_with_code":30,"rows_with_paper_page":32,"rows_dated":32,"rows_using_additional_data":4},"rows":[{"rank_in_archive_order":1,"model":"Cooperative Foundational Models","metrics":{"AP 0.5":"50.3"},"uses_additional_data":false,"paper_date":"2023-11-19","paper":"/paper/enhancing-novel-object-detection-via","paper_url":"https://arxiv.org/abs/2311.12068v4","paper_title":"Enhancing Novel Object Detection via Cooperative Foundational Models","code":"https://github.com/rohit901/cooperative-foundational-models","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"DE-ViT","metrics":{"AP 0.5":"50"},"uses_additional_data":false,"paper_date":"2023-09-22","paper":"/paper/detect-every-thing-with-few-examples","paper_url":"https://arxiv.org/abs/2309.12969v4","paper_title":"Detect Everything with Few Examples","code":"https://github.com/mlzxy/devit","n_code_links":1,"syntology":{"n_ran":15,"n_unverified":5,"n_samples":20,"n_pointer_only_licence":0}},{"rank_in_archive_order":3,"model":"Yolov8-nano","metrics":{"AP 0.5":"47.2"},"uses_additional_data":true,"paper_date":"2023-10-31","paper":"/paper/yolov8-based-visual-detection-of-road-hazards","paper_url":"https://arxiv.org/abs/2311.00073v1","paper_title":"YOLOv8-Based Visual Detection of Road Hazards: Potholes, Sewer Covers, and Manholes","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":4,"model":"DITO","metrics":{"AP 0.5":"46.1"},"uses_additional_data":false,"paper_date":"2023-09-29","paper":"/paper/detection-oriented-image-text-pretraining-for","paper_url":"https://arxiv.org/abs/2310.00161v2","paper_title":"Region-centric Image-Language Pretraining for Open-Vocabulary Detection","code":"https://github.com/google-research/google-research/tree/master/fvlm/dito","n_code_links":2,"syntology":null},{"rank_in_archive_order":5,"model":"OV-DQUO(RN50x4)","metrics":{"AP 0.5":"45.6"},"uses_additional_data":false,"paper_date":"2024-05-28","paper":"/paper/ov-dquo-open-vocabulary-detr-with-denoising","paper_url":"https://arxiv.org/abs/2405.17913v2","paper_title":"OV-DQUO: Open-Vocabulary DETR with Denoising Text Query Training and Open-World Unknown Objects Supervision","code":"https://github.com/xiaomoguhz/ov-dquo","n_code_links":1,"syntology":{"n_ran":9,"n_unverified":2,"n_samples":11,"n_pointer_only_licence":0}},{"rank_in_archive_order":6,"model":"LP-OVOD (OWL-ViT Proposals)","metrics":{"AP 0.5":"44.9"},"uses_additional_data":false,"paper_date":"2023-10-26","paper":"/paper/lp-ovod-open-vocabulary-object-detection-by","paper_url":"https://arxiv.org/abs/2310.17109v2","paper_title":"LP-OVOD: Open-Vocabulary Object Detection by Linear Probing","code":"https://github.com/vinairesearch/lp-ovod","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":7,"model":"CLIPSelf","metrics":{"AP 0.5":"44.3"},"uses_additional_data":false,"paper_date":"2023-10-02","paper":"/paper/clipself-vision-transformer-distills-itself","paper_url":"https://arxiv.org/abs/2310.01403v2","paper_title":"CLIPSelf: Vision Transformer Distills Itself for Open-Vocabulary Dense Prediction","code":"https://github.com/wusize/clipself","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":4,"n_samples":6,"n_pointer_only_licence":6}},{"rank_in_archive_order":8,"model":"CORA+","metrics":{"AP 0.5":"43.1"},"uses_additional_data":false,"paper_date":"2023-03-23","paper":"/paper/cora-adapting-clip-for-open-vocabulary","paper_url":"https://arxiv.org/abs/2303.13076v1","paper_title":"CORA: Adapting CLIP for Open-Vocabulary Detection with Region Prompting and Anchor Pre-Matching","code":"https://github.com/tgxs002/cora","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":1,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":9,"model":"BARON","metrics":{"AP 0.5":"42.7"},"uses_additional_data":false,"paper_date":"2023-02-27","paper":"/paper/aligning-bag-of-regions-for-open-vocabulary","paper_url":"https://arxiv.org/abs/2302.13996v1","paper_title":"Aligning Bag of Regions for Open-Vocabulary Object Detection","code":"https://github.com/wusize/ovdet","n_code_links":1,"syntology":null},{"rank_in_archive_order":10,"model":"SIA-OVD (RN50x4)","metrics":{"AP 0.5":"41.9"},"uses_additional_data":false,"paper_date":"2024-10-08","paper":"/paper/sia-ovd-shape-invariant-adapter-for-bridging","paper_url":"https://arxiv.org/abs/2410.05650v1","paper_title":"SIA-OVD: Shape-Invariant Adapter for Bridging the Image-Region Gap in Open-Vocabulary Detection","code":"https://github.com/pku-icst-mipl/sia-ovd_acmmm2024","n_code_links":1,"syntology":null},{"rank_in_archive_order":11,"model":"CORA","metrics":{"AP 0.5":"41.7"},"uses_additional_data":false,"paper_date":"2023-03-23","paper":"/paper/cora-adapting-clip-for-open-vocabulary","paper_url":"https://arxiv.org/abs/2303.13076v1","paper_title":"CORA: Adapting CLIP for Open-Vocabulary Detection with Region Prompting and Anchor Pre-Matching","code":"https://github.com/tgxs002/cora","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":1,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":12,"model":"RALF","metrics":{"AP 0.5":"41.3"},"uses_additional_data":false,"paper_date":"2024-04-08","paper":"/paper/retrieval-augmented-open-vocabulary-object","paper_url":"https://arxiv.org/abs/2404.05687v1","paper_title":"Retrieval-Augmented Open-Vocabulary Object Detection","code":"https://github.com/mlvlab/RALF","n_code_links":1,"syntology":null},{"rank_in_archive_order":13,"model":"LP-OVOD","metrics":{"AP 0.5":"40.5"},"uses_additional_data":false,"paper_date":"2023-10-26","paper":"/paper/lp-ovod-open-vocabulary-object-detection-by","paper_url":"https://arxiv.org/abs/2310.17109v2","paper_title":"LP-OVOD: Open-Vocabulary Object Detection by Linear Probing","code":"https://github.com/vinairesearch/lp-ovod","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":14,"model":"Region-CLIP (RN50x4-C4)","metrics":{"AP 0.5":"39.3"},"uses_additional_data":true,"paper_date":"2021-12-16","paper":"/paper/regionclip-region-based-language-image","paper_url":"https://arxiv.org/abs/2112.09106v1","paper_title":"RegionCLIP: Region-based Language-Image Pretraining","code":"https://github.com/microsoft/regionclip","n_code_links":1,"syntology":null},{"rank_in_archive_order":15,"model":"OV-DQUO(R50)","metrics":{"AP 0.5":"39.2"},"uses_additional_data":false,"paper_date":"2024-05-28","paper":"/paper/ov-dquo-open-vocabulary-detr-with-denoising","paper_url":"https://arxiv.org/abs/2405.17913v2","paper_title":"OV-DQUO: Open-Vocabulary DETR with Denoising Text Query Training and Open-World Unknown Objects Supervision","code":"https://github.com/xiaomoguhz/ov-dquo","n_code_links":1,"syntology":{"n_ran":9,"n_unverified":2,"n_samples":11,"n_pointer_only_licence":0}},{"rank_in_archive_order":16,"model":"Object-Centric-OVD","metrics":{"AP 0.5":"36.9"},"uses_additional_data":false,"paper_date":"2022-07-07","paper":"/paper/bridging-the-gap-between-object-and-image","paper_url":"https://arxiv.org/abs/2207.03482v3","paper_title":"Bridging the Gap between Object and Image-level Representations for Open-Vocabulary Detection","code":"https://github.com/mmaaz60/mvits_for_class_agnostic_od","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":1,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":17,"model":"CLIM (RN50)","metrics":{"AP 0.5":"36.9"},"uses_additional_data":false,"paper_date":"2023-12-18","paper":"/paper/clim-contrastive-language-image-mosaic-for","paper_url":"https://arxiv.org/abs/2312.11376v2","paper_title":"CLIM: Contrastive Language-Image Mosaic for Region Representation","code":"https://github.com/wusize/clim","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":2,"n_samples":3,"n_pointer_only_licence":3}},{"rank_in_archive_order":18,"model":"OADP (G-OVD)","metrics":{"AP 0.5":"35.6"},"uses_additional_data":false,"paper_date":"2023-03-10","paper":"/paper/object-aware-distillation-pyramid-for-open","paper_url":"https://arxiv.org/abs/2303.05892v1","paper_title":"Object-Aware Distillation Pyramid for Open-Vocabulary Object Detection","code":"https://github.com/lutingwang/oadp","n_code_links":1,"syntology":null},{"rank_in_archive_order":19,"model":"SIA-OVD (RN50)","metrics":{"AP 0.5":"35.5"},"uses_additional_data":false,"paper_date":"2024-10-08","paper":"/paper/sia-ovd-shape-invariant-adapter-for-bridging","paper_url":"https://arxiv.org/abs/2410.05650v1","paper_title":"SIA-OVD: Shape-Invariant Adapter for Bridging the Image-Region Gap in Open-Vocabulary Detection","code":"https://github.com/pku-icst-mipl/sia-ovd_acmmm2024","n_code_links":1,"syntology":null},{"rank_in_archive_order":20,"model":"VL-PLM (RN50)","metrics":{"AP 0.5":"34.4"},"uses_additional_data":false,"paper_date":"2022-07-18","paper":"/paper/exploiting-unlabeled-data-with-vision-and","paper_url":"https://arxiv.org/abs/2207.08954v1","paper_title":"Exploiting Unlabeled Data with Vision and Language Models for Object Detection","code":"https://github.com/xiaofeng94/vl-plm","n_code_links":1,"syntology":null},{"rank_in_archive_order":21,"model":"CFM-ViT","metrics":{"AP 0.5":"34.1"},"uses_additional_data":false,"paper_date":"2023-09-02","paper":"/paper/contrastive-feature-masking-open-vocabulary","paper_url":"https://arxiv.org/abs/2309.00775v1","paper_title":"Contrastive Feature Masking Open-Vocabulary Vision Transformer","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":22,"model":"MEDet (RN50)","metrics":{"AP 0.5":" 32.6"},"uses_additional_data":false,"paper_date":"2022-06-22","paper":"/paper/open-vocabulary-object-detection-with","paper_url":"https://arxiv.org/abs/2206.11134v4","paper_title":"Open Vocabulary Object Detection with Proposal Mining and Prediction Equalization","code":"https://github.com/peixianchen/medet","n_code_links":2,"syntology":{"n_ran":7,"n_unverified":2,"n_samples":9,"n_pointer_only_licence":0}},{"rank_in_archive_order":23,"model":"Region-CLIP (RN50-C4)","metrics":{"AP 0.5":"31.4"},"uses_additional_data":true,"paper_date":"2021-12-16","paper":"/paper/regionclip-region-based-language-image","paper_url":"https://arxiv.org/abs/2112.09106v1","paper_title":"RegionCLIP: Region-based Language-Image Pretraining","code":"https://github.com/microsoft/regionclip","n_code_links":1,"syntology":null},{"rank_in_archive_order":24,"model":"OVAD-Baseline","metrics":{"AP 0.5":"30.0"},"uses_additional_data":false,"paper_date":"2022-11-23","paper":"/paper/open-vocabulary-attribute-detection","paper_url":"https://arxiv.org/abs/2211.12914v2","paper_title":"Open-vocabulary Attribute Detection","code":"https://github.com/OVAD-Benchmark/ovad-bechmark-code","n_code_links":1,"syntology":{"n_ran":8,"n_unverified":2,"n_samples":10,"n_pointer_only_licence":0}},{"rank_in_archive_order":25,"model":"OADP","metrics":{"AP 0.5":"30.0"},"uses_additional_data":false,"paper_date":"2023-03-10","paper":"/paper/object-aware-distillation-pyramid-for-open","paper_url":"https://arxiv.org/abs/2303.05892v1","paper_title":"Object-Aware Distillation Pyramid for Open-Vocabulary Object Detection","code":"https://github.com/lutingwang/oadp","n_code_links":1,"syntology":null},{"rank_in_archive_order":26,"model":"OV-DERT","metrics":{"AP 0.5":"29.4"},"uses_additional_data":false,"paper_date":"2022-03-22","paper":"/paper/open-vocabulary-detr-with-conditional","paper_url":"https://arxiv.org/abs/2203.11876v2","paper_title":"Open-Vocabulary DETR with Conditional Matching","code":"https://github.com/yuhangzang/ov-detr","n_code_links":4,"syntology":{"n_ran":6,"n_unverified":2,"n_samples":8,"n_pointer_only_licence":4}},{"rank_in_archive_order":27,"model":"LocOv (RN50-C4)","metrics":{"AP 0.5":"28.6"},"uses_additional_data":false,"paper_date":"2022-05-12","paper":"/paper/localized-vision-language-matching-for-open","paper_url":"https://arxiv.org/abs/2205.06160v2","paper_title":"Localized Vision-Language Matching for Open-vocabulary Object Detection","code":"https://github.com/lmb-freiburg/locov","n_code_links":1,"syntology":null},{"rank_in_archive_order":28,"model":"Detic","metrics":{"AP 0.5":"27.8"},"uses_additional_data":false,"paper_date":"2022-01-07","paper":"/paper/detecting-twenty-thousand-classes-using-image","paper_url":"https://arxiv.org/abs/2201.02605v3","paper_title":"Detecting Twenty-thousand Classes using Image-level Supervision","code":"https://github.com/facebookresearch/Detic","n_code_links":1,"syntology":null},{"rank_in_archive_order":29,"model":"ViLD","metrics":{"AP 0.5":"27.6"},"uses_additional_data":true,"paper_date":"2021-04-28","paper":"/paper/zero-shot-detection-via-vision-and-language","paper_url":"https://arxiv.org/abs/2104.13921v3","paper_title":"Open-vocabulary Object Detection via Vision and Language Knowledge Distillation","code":"https://github.com/tensorflow/tpu","n_code_links":4,"syntology":null},{"rank_in_archive_order":30,"model":"OVR-CNN","metrics":{"AP 0.5":"22.8"},"uses_additional_data":false,"paper_date":"2020-11-20","paper":"/paper/open-vocabulary-object-detection-using","paper_url":"https://arxiv.org/abs/2011.10678v2","paper_title":"Open-Vocabulary Object Detection Using Captions","code":"https://github.com/alirezazareian/ovr-cnn","n_code_links":1,"syntology":null},{"rank_in_archive_order":31,"model":"HierKD","metrics":{"AP 0.5":"20.3"},"uses_additional_data":false,"paper_date":"2022-03-20","paper":"/paper/open-vocabulary-one-stage-detection-with","paper_url":"https://arxiv.org/abs/2203.10593v1","paper_title":"Open-Vocabulary One-Stage Detection with Hierarchical Visual-Language Knowledge Distillation","code":"https://github.com/mengqidyangge/hierkd","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":2,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":32,"model":"Yolov8","metrics":{"AP 0.5":"0.5"},"uses_additional_data":false,"paper_date":"2024-02-14","paper":"/paper/yolov8-am-yolov8-with-attention-mechanisms","paper_url":"https://arxiv.org/abs/2402.09329v5","paper_title":"YOLOv8-AM: YOLOv8 Based on Effective Attention Mechanisms for Pediatric Wrist Fracture Detection","code":"https://github.com/ruiyangju/fracture_detection_improved_yolov8","n_code_links":1,"syntology":null}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,821 of the 9,623 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9623,"papers_checked":6821,"papers_extracted_not_yet_verified":65,"boards_without_verdict":29,"papers_not_yet_extracted":2737},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-25T09:33:49+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":14,"rows_with_any_sample_ran":14,"distinct_papers_with_graph_line":11,"distinct_papers_with_any_sample_ran":11,"samples_over_distinct_papers":{"n_ran":56,"n_unverified":23,"n_samples":79,"n_pointer_only_licence":15,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":69,"n_unverified":26,"n_samples":95,"n_pointer_only_licence":17,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}