{"url":"/sota/semi-supervised-object-detection-on-coco-5","task":{"name":"Semi-Supervised Object Detection","url":"/task/semi-supervised-object-detection","note":null},"dataset":{"name":"COCO 5% labeled data","url":null},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"Semi-supervised object detection uses both labeled data and unlabeled data for training. It not only reduces the annotation burden for training high-performance object detectors but also further improves the object detector by using a large number of unlabeled data.","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":["mAP"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"mAP":"higher"}},"counts":{"rows":23,"rows_with_code":19,"rows_with_paper_page":23,"rows_dated":23,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"Semi-DETR","metrics":{"mAP":"40.1"},"uses_additional_data":false,"paper_date":"2023-07-16","paper":"/paper/semi-detr-semi-supervised-object-detection-1","paper_url":"https://arxiv.org/abs/2307.08095v1","paper_title":"Semi-DETR: Semi-Supervised Object Detection with Detection Transformers","code":"https://github.com/PaddlePaddle/PaddleDetection","n_code_links":3,"syntology":null},{"rank_in_archive_order":2,"model":"MixPL","metrics":{"mAP":"40.1"},"uses_additional_data":false,"paper_date":"2023-12-12","paper":"/paper/mixed-pseudo-labels-for-semi-supervised","paper_url":"https://arxiv.org/abs/2312.07006v1","paper_title":"Mixed Pseudo Labels for Semi-Supervised Object Detection","code":"https://github.com/czm369/mixpl","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"ARSL","metrics":{"mAP":"34.45"},"uses_additional_data":false,"paper_date":"2023-03-27","paper":"/paper/ambiguity-resistant-semi-supervised-learning","paper_url":"https://arxiv.org/abs/2303.14960v1","paper_title":"Ambiguity-Resistant Semi-Supervised Learning for Dense Object Detection","code":"https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/semi_det/arsl","n_code_links":1,"syntology":null},{"rank_in_archive_order":4,"model":"Efficient Teacher","metrics":{"mAP":"34.11"},"uses_additional_data":false,"paper_date":"2023-02-15","paper":"/paper/efficient-teacher-semi-supervised-object","paper_url":"https://arxiv.org/abs/2302.07577v3","paper_title":"Efficient Teacher: Semi-Supervised Object Detection for YOLOv5","code":"https://github.com/modelscope/modelscope","n_code_links":4,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":3}},{"rank_in_archive_order":5,"model":"MixTeacher-FRCNN","metrics":{"mAP":"34.06"},"uses_additional_data":false,"paper_date":"2023-03-16","paper":"/paper/mixteacher-mining-promising-labels-with-mixed","paper_url":"https://arxiv.org/abs/2303.09061v1","paper_title":"MixTeacher: Mining Promising Labels with Mixed Scale Teacher for Semi-Supervised Object Detection","code":"https://github.com/lliuz/mixteacher","n_code_links":1,"syntology":null},{"rank_in_archive_order":6,"model":"MixTeacher-FCOS","metrics":{"mAP":"33.42"},"uses_additional_data":false,"paper_date":"2023-03-16","paper":"/paper/mixteacher-mining-promising-labels-with-mixed","paper_url":"https://arxiv.org/abs/2303.09061v1","paper_title":"MixTeacher: Mining Promising Labels with Mixed Scale Teacher for Semi-Supervised Object Detection","code":"https://github.com/lliuz/mixteacher","n_code_links":1,"syntology":null},{"rank_in_archive_order":7,"model":"Dense Teacher","metrics":{"mAP":"33.01"},"uses_additional_data":false,"paper_date":"2022-07-06","paper":"/paper/dense-teacher-dense-pseudo-labels-for-semi","paper_url":"https://arxiv.org/abs/2207.02541v2","paper_title":"Dense Teacher: Dense Pseudo-Labels for Semi-supervised Object Detection","code":"https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/semi_det","n_code_links":2,"syntology":{"n_ran":0,"n_unverified":3,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":8,"model":"PseCo","metrics":{"mAP":"32.5"},"uses_additional_data":false,"paper_date":"2022-03-30","paper":"/paper/pseco-pseudo-labeling-and-consistency","paper_url":"https://arxiv.org/abs/2203.16317v2","paper_title":"PseCo: Pseudo Labeling and Consistency Training for Semi-Supervised Object Detection","code":"https://github.com/ligang-cs/PseCo","n_code_links":1,"syntology":null},{"rank_in_archive_order":9,"model":"Revisiting Class Imbalance","metrics":{"mAP":"32.21"},"uses_additional_data":false,"paper_date":"2023-06-04","paper":"/paper/revisiting-class-imbalance-for-end-to-end","paper_url":"https://arxiv.org/abs/2306.02268v1","paper_title":"Revisiting Class Imbalance for End-to-end Semi-Supervised Object Detection","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":10,"model":"Polishing Teacher","metrics":{"mAP":"32.10±0.15"},"uses_additional_data":false,"paper_date":"2022-07-17","paper":"/paper/mind-the-gap-polishing-pseudo-labels-for","paper_url":"https://arxiv.org/abs/2207.08185v2","paper_title":"Mind the Gap: Polishing Pseudo labels for Accurate Semi-supervised Object Detection","code":"https://github.com/snowdusky/dualpolishlearning","n_code_links":1,"syntology":null},{"rank_in_archive_order":11,"model":"VC","metrics":{"mAP":"32.05"},"uses_additional_data":false,"paper_date":"2022-07-07","paper":"/paper/semi-supervised-object-detection-via-virtual-1","paper_url":"https://arxiv.org/abs/2207.03433v2","paper_title":"Semi-supervised Object Detection via Virtual Category Learning","code":"https://github.com/geoffreychen777/vc","n_code_links":1,"syntology":null},{"rank_in_archive_order":12,"model":"Unbiased Teacher v2","metrics":{"mAP":"31.85±0.09"},"uses_additional_data":false,"paper_date":"2022-06-19","paper":"/paper/unbiased-teacher-v2-semi-supervised-object-1","paper_url":"https://arxiv.org/abs/2206.09500v1","paper_title":"Unbiased Teacher v2: Semi-supervised Object Detection for Anchor-free and Anchor-based Detectors","code":"https://github.com/facebookresearch/unbiased-teacher-v2","n_code_links":1,"syntology":null},{"rank_in_archive_order":13,"model":"Adaptive Class-Rebalancing","metrics":{"mAP":"31.35±0.13"},"uses_additional_data":false,"paper_date":"2021-07-11","paper":"/paper/semi-supervised-object-detection-with-1","paper_url":"https://arxiv.org/abs/2107.05031v1","paper_title":"Semi-Supervised Object Detection with Adaptive Class-Rebalancing Self-Training","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":14,"model":"Soft Teacher + Swin-L(HTC++, multi-scale)","metrics":{"mAP":"30.74"},"uses_additional_data":false,"paper_date":"2021-06-16","paper":"/paper/end-to-end-semi-supervised-object-detection","paper_url":"https://arxiv.org/abs/2106.09018v3","paper_title":"End-to-End Semi-Supervised Object Detection with Soft Teacher","code":"https://github.com/microsoft/SoftTeacher","n_code_links":8,"syntology":null},{"rank_in_archive_order":15,"model":"SSOD with OCL and RUPL","metrics":{"mAP":"30.66"},"uses_additional_data":false,"paper_date":"2022-12-06","paper":"/paper/semi-supervised-object-detection-with-object","paper_url":"https://arxiv.org/abs/2212.02747v1","paper_title":"Semi-Supervised Object Detection with Object-wise Contrastive Learning and Regression Uncertainty","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":16,"model":"ASTOD","metrics":{"mAP":"30.43"},"uses_additional_data":false,"paper_date":"2022-12-07","paper":"/paper/adaptive-self-training-for-object-detection","paper_url":"https://arxiv.org/abs/2212.05911v2","paper_title":"Adaptive Self-Training for Object Detection","code":"https://github.com/rvandeghen/ASTOD","n_code_links":1,"syntology":null},{"rank_in_archive_order":17,"model":"Omni-DETR","metrics":{"mAP":"30.2"},"uses_additional_data":false,"paper_date":"2022-03-30","paper":"/paper/omni-detr-omni-supervised-object-detection","paper_url":"https://arxiv.org/abs/2203.16089v1","paper_title":"Omni-DETR: Omni-Supervised Object Detection with Transformers","code":"https://github.com/amazon-research/omni-detr","n_code_links":1,"syntology":null},{"rank_in_archive_order":18,"model":"MUM","metrics":{"mAP":"28.52"},"uses_additional_data":false,"paper_date":"2021-11-22","paper":"/paper/mum-mix-image-tiles-and-unmix-feature-tiles","paper_url":"https://arxiv.org/abs/2111.10958v2","paper_title":"MUM : Mix Image Tiles and UnMix Feature Tiles for Semi-Supervised Object Detection","code":"https://github.com/jongmokkim/mix-unmix","n_code_links":1,"syntology":null},{"rank_in_archive_order":19,"model":"RPL","metrics":{"mAP":"28.4 ± 0.15"},"uses_additional_data":false,"paper_date":"2021-06-01","paper":"/paper/rethinking-pseudo-labels-for-semi-supervised","paper_url":"https://arxiv.org/abs/2106.00168v2","paper_title":"Rethinking Pseudo Labels for Semi-Supervised Object Detection","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":20,"model":"Unbiased Teacher","metrics":{"mAP":"28.27± 0.11"},"uses_additional_data":false,"paper_date":"2021-02-18","paper":"/paper/unbiased-teacher-for-semi-supervised-object-1","paper_url":"https://arxiv.org/abs/2102.09480v1","paper_title":"Unbiased Teacher for Semi-Supervised Object Detection","code":"https://github.com/facebookresearch/unbiased-teacher","n_code_links":4,"syntology":null},{"rank_in_archive_order":21,"model":"Instant Teaching","metrics":{"mAP":"26.75"},"uses_additional_data":false,"paper_date":"2021-03-21","paper":"/paper/instant-teaching-an-end-to-end-semi","paper_url":"https://arxiv.org/abs/2103.11402v1","paper_title":"Instant-Teaching: An End-to-End Semi-Supervised Object Detection Framework","code":"https://github.com/hattrickcr7/SoftTeacher","n_code_links":1,"syntology":null},{"rank_in_archive_order":22,"model":"DETReg","metrics":{"mAP":"24.80±0.2"},"uses_additional_data":false,"paper_date":"2021-06-08","paper":"/paper/detreg-unsupervised-pretraining-with-region","paper_url":"https://arxiv.org/abs/2106.04550v5","paper_title":"DETReg: Unsupervised Pretraining with Region Priors for Object Detection","code":"https://github.com/amirbar/detreg","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":3,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":23,"model":"STAC","metrics":{"mAP":"24.38±0.12"},"uses_additional_data":false,"paper_date":"2020-05-10","paper":"/paper/a-simple-semi-supervised-learning-framework","paper_url":"https://arxiv.org/abs/2005.04757v2","paper_title":"A Simple Semi-Supervised Learning Framework for Object Detection","code":"https://github.com/google-research/ssl_detection","n_code_links":7,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0}}],"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 6,264 of the 9,581 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":9581,"papers_checked":6264,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":3316},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-24T18:15:14+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":4,"rows_with_any_sample_ran":2,"distinct_papers_with_graph_line":4,"distinct_papers_with_any_sample_ran":2,"samples_over_distinct_papers":{"n_ran":7,"n_unverified":7,"n_samples":14,"n_pointer_only_licence":3,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":7,"n_unverified":7,"n_samples":14,"n_pointer_only_licence":3,"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"}}}