{"url":"/sota/source-free-object-detection-on-cityscapes-to","task":{"name":"Source Free Object Detection","url":"/task/source-free-object-detection","note":null},"dataset":{"name":"Cityscapes to Foggy Cityscapes","url":"/dataset/foggy-cityscapes"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"Source-Free Object Detection (SFOD) is a domain adaptation challenge in which only the pretrained source model weights are available during adaptation, with no access to the source data. The model must adapt solely using unlabeled samples from the target domain","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":["AP50"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"AP50":null}},"counts":{"rows":13,"rows_with_code":8,"rows_with_paper_page":13,"rows_dated":13,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"GT","metrics":{"AP50":"50.8"},"uses_additional_data":false,"paper_date":"2025-04-21","paper":"/paper/context-aware-grounded-teacher-for-source-1","paper_url":"https://arxiv.org/abs/2504.15404v1","paper_title":"Context Aware Grounded Teacher for Source Free Object Detection","code":"https://github.com/Tajamul21/Grounded_Teacher","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"SF-UT","metrics":{"AP50":"45.0"},"uses_additional_data":false,"paper_date":"2024-07-10","paper":"/paper/simplifying-source-free-domain-adaptation-for","paper_url":"https://arxiv.org/abs/2407.07586v1","paper_title":"Simplifying Source-Free Domain Adaptation for Object Detection: Effective Self-Training Strategies and Performance Insights","code":"https://github.com/epfl-imos/simple-sfod","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"LPLD","metrics":{"AP50":"40.9"},"uses_additional_data":false,"paper_date":"2024-07-18","paper":"/paper/enhancing-source-free-domain-adaptive-object","paper_url":"https://arxiv.org/abs/2407.13524v1","paper_title":"Enhancing Source-Free Domain Adaptive Object Detection with Low-confidence Pseudo Label Distillation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":4,"model":"PETS","metrics":{"AP50":"40.3"},"uses_additional_data":false,"paper_date":"2023-11-23","paper":"/paper/periodically-exchange-teacher-student-for-1","paper_url":"https://arxiv.org/abs/2311.13930v1","paper_title":"Periodically Exchange Teacher-Student for Source-Free Object Detection","code":"https://github.com/RainbowNebula/PETS","n_code_links":1,"syntology":null},{"rank_in_archive_order":5,"model":"DACA","metrics":{"AP50":"39.9"},"uses_additional_data":false,"paper_date":"2024-02-09","paper":"/paper/multi-source-free-domain-adaptation-via","paper_url":"https://arxiv.org/abs/2402.06213v1","paper_title":"Multi-source-free Domain Adaptation via Uncertainty-aware Adaptive Distillation","code":"https://github.com/YXSong000/UAD","n_code_links":1,"syntology":null},{"rank_in_archive_order":6,"model":"HCL","metrics":{"AP50":"39.7"},"uses_additional_data":false,"paper_date":"2021-10-07","paper":"/paper/model-adaptation-historical-contrastive","paper_url":"https://arxiv.org/abs/2110.03374v6","paper_title":"Model Adaptation: Historical Contrastive Learning for Unsupervised Domain Adaptation without Source Data","code":"https://github.com/jxhuang0508/HCL","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":7,"model":"LPU","metrics":{"AP50":"38.8"},"uses_additional_data":false,"paper_date":"2023-10-19","paper":"/paper/exploiting-low-confidence-pseudo-labels-for","paper_url":"https://arxiv.org/abs/2310.12705v1","paper_title":"Exploiting Low-confidence Pseudo-labels for Source-free Object Detection","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":8,"model":"IRG","metrics":{"AP50":"37.1"},"uses_additional_data":false,"paper_date":"2022-03-29","paper":"/paper/instance-relation-graph-guided-source-free","paper_url":"https://arxiv.org/abs/2203.15793v4","paper_title":"Instance Relation Graph Guided Source-Free Domain Adaptive Object Detection","code":"https://github.com/vibashan/irg-sfda","n_code_links":1,"syntology":null},{"rank_in_archive_order":9,"model":"LODS","metrics":{"AP50":"35.8"},"uses_additional_data":false,"paper_date":"2022-01-01","paper":"/paper/source-free-object-detection-by-learning-to","paper_url":"http://openaccess.thecvf.com//content/CVPR2022/html/Li_Source-Free_Object_Detection_by_Learning_To_Overlook_Domain_Style_CVPR_2022_paper.html","paper_title":"Source-Free Object Detection by Learning To Overlook Domain Style","code":"https://github.com/Flashkong/Source-Free-Object-Detection-by-Learning-to-Overlook-Domain-Style","n_code_links":1,"syntology":null},{"rank_in_archive_order":10,"model":"AASFOD","metrics":{"AP50":"35.4"},"uses_additional_data":false,"paper_date":"2023-01-11","paper":"/paper/adversarial-alignment-for-source-free-object","paper_url":"https://arxiv.org/abs/2301.04265v1","paper_title":"Adversarial Alignment for Source Free Object Detection","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":11,"model":"MT","metrics":{"AP50":"34.3"},"uses_additional_data":false,"paper_date":"2017-03-06","paper":"/paper/mean-teachers-are-better-role-models-weight","paper_url":"http://arxiv.org/abs/1703.01780v6","paper_title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results","code":"https://github.com/CuriousAI/mean-teacher","n_code_links":8,"syntology":{"n_ran":6,"n_unverified":0,"n_samples":6,"n_pointer_only_licence":6}},{"rank_in_archive_order":12,"model":"SFOD-Mosaic","metrics":{"AP50":"33.5"},"uses_additional_data":false,"paper_date":"2020-12-10","paper":"/paper/a-free-lunch-for-unsupervised-domain-adaptive","paper_url":"https://arxiv.org/abs/2012.05400v1","paper_title":"A Free Lunch for Unsupervised Domain Adaptive Object Detection without Source Data","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":13,"model":"SFOD","metrics":{"AP50":"30.6"},"uses_additional_data":false,"paper_date":"2020-12-10","paper":"/paper/a-free-lunch-for-unsupervised-domain-adaptive","paper_url":"https://arxiv.org/abs/2012.05400v1","paper_title":"A Free Lunch for Unsupervised Domain Adaptive Object Detection without Source Data","code":null,"n_code_links":0,"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 6,885 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":6885,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"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":2,"rows_with_any_sample_ran":1,"distinct_papers_with_graph_line":2,"distinct_papers_with_any_sample_ran":1,"samples_over_distinct_papers":{"n_ran":6,"n_unverified":1,"n_samples":7,"n_pointer_only_licence":6,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":6,"n_unverified":1,"n_samples":7,"n_pointer_only_licence":6,"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"}}}