{"url":"/sota/long-tail-learning-on-voc-mlt","task":{"name":"Long-tail Learning","url":"/task/long-tail-learning","note":null},"dataset":{"name":"VOC-MLT","url":"/dataset/voc-mlt"},"category":"Methodology","categories":["Methodology"],"category_note":null,"description":"Long-tailed learning, one of the most challenging problems in visual recognition, aims to train well-performing models from a large number of images that follow a long-tailed class distribution.","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":["Average mAP"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Average mAP":"higher"}},"counts":{"rows":13,"rows_with_code":11,"rows_with_paper_page":13,"rows_dated":13,"rows_using_additional_data":4},"rows":[{"rank_in_archive_order":1,"model":"LMPT(ViT-B/16)","metrics":{"Average mAP":"87.88"},"uses_additional_data":true,"paper_date":"2023-05-08","paper":"/paper/lmpt-prompt-tuning-with-class-specific","paper_url":"https://arxiv.org/abs/2305.04536v2","paper_title":"LMPT: Prompt Tuning with Class-Specific Embedding Loss for Long-tailed Multi-Label Visual Recognition","code":"https://github.com/richard-peng-xia/LMPT","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":9,"n_samples":9,"n_pointer_only_licence":0}},{"rank_in_archive_order":2,"model":"CLIP(ViT-B/16)","metrics":{"Average mAP":"85.77"},"uses_additional_data":true,"paper_date":"2021-02-26","paper":"/paper/learning-transferable-visual-models-from","paper_url":"https://arxiv.org/abs/2103.00020v1","paper_title":"Learning Transferable Visual Models From Natural Language Supervision","code":"https://github.com/openai/CLIP","n_code_links":82,"syntology":{"n_ran":16,"n_unverified":4,"n_samples":20,"n_pointer_only_licence":16}},{"rank_in_archive_order":3,"model":"LMPT(ResNet-50)","metrics":{"Average mAP":"85.44"},"uses_additional_data":true,"paper_date":"2023-05-08","paper":"/paper/lmpt-prompt-tuning-with-class-specific","paper_url":"https://arxiv.org/abs/2305.04536v2","paper_title":"LMPT: Prompt Tuning with Class-Specific Embedding Loss for Long-tailed Multi-Label Visual Recognition","code":"https://github.com/richard-peng-xia/LMPT","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":9,"n_samples":9,"n_pointer_only_licence":0}},{"rank_in_archive_order":4,"model":"CLIP(ResNet-50)","metrics":{"Average mAP":"84.30"},"uses_additional_data":true,"paper_date":"2021-02-26","paper":"/paper/learning-transferable-visual-models-from","paper_url":"https://arxiv.org/abs/2103.00020v1","paper_title":"Learning Transferable Visual Models From Natural Language Supervision","code":"https://github.com/openai/CLIP","n_code_links":82,"syntology":{"n_ran":16,"n_unverified":4,"n_samples":20,"n_pointer_only_licence":16}},{"rank_in_archive_order":5,"model":"LTML(ResNet-50)","metrics":{"Average mAP":"81.44"},"uses_additional_data":false,"paper_date":"2021-06-19","paper":"/paper/long-tailed-multi-label-visual-recognition-by","paper_url":"http://openaccess.thecvf.com//content/CVPR2021/html/Guo_Long-Tailed_Multi-Label_Visual_Recognition_by_Collaborative_Training_on_Uniform_and_CVPR_2021_paper.html","paper_title":"Long-Tailed Multi-Label Visual Recognition by Collaborative Training on Uniform and Re-Balanced Samplings","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":6,"model":"PG Loss(ResNet-50)","metrics":{"Average mAP":"80.37"},"uses_additional_data":false,"paper_date":"2023-06-26","paper":"/paper/probability-guided-loss-for-long-tailed-multi","paper_url":"https://ojs.aaai.org/index.php/AAAI/article/view/25244","paper_title":"Probability Guided Loss for Long-Tailed Multi-Label Image Classification","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":7,"model":"DB Focal(ResNet-50)","metrics":{"Average mAP":"78.94"},"uses_additional_data":false,"paper_date":"2020-07-19","paper":"/paper/distribution-balanced-loss-for-multi-label","paper_url":"https://arxiv.org/abs/2007.09654v4","paper_title":"Distribution-Balanced Loss for Multi-Label Classification in Long-Tailed Datasets","code":"https://github.com/wutong16/DistributionBalancedLoss","n_code_links":1,"syntology":null},{"rank_in_archive_order":8,"model":"RS(ResNet-50)","metrics":{"Average mAP":"75.38"},"uses_additional_data":false,"paper_date":"2015-12-18","paper":"/paper/relay-backpropagation-for-effective-learning","paper_url":"http://arxiv.org/abs/1512.05830v2","paper_title":"Relay Backpropagation for Effective Learning of Deep Convolutional Neural Networks","code":"https://github.com/craston/object_detection_cib","n_code_links":1,"syntology":null},{"rank_in_archive_order":9,"model":"CB Focal(ResNet-50)","metrics":{"Average mAP":"75.24"},"uses_additional_data":false,"paper_date":"2019-01-16","paper":"/paper/class-balanced-loss-based-on-effective-number","paper_url":"http://arxiv.org/abs/1901.05555v1","paper_title":"Class-Balanced Loss Based on Effective Number of Samples","code":"https://github.com/vandit15/Class-balanced-loss-pytorch","n_code_links":11,"syntology":{"n_ran":7,"n_unverified":20,"n_samples":27,"n_pointer_only_licence":0}},{"rank_in_archive_order":10,"model":"Focal Loss(ResNet-50)","metrics":{"Average mAP":"73.88"},"uses_additional_data":false,"paper_date":"2017-08-07","paper":"/paper/focal-loss-for-dense-object-detection","paper_url":"http://arxiv.org/abs/1708.02002v2","paper_title":"Focal Loss for Dense Object Detection","code":"https://github.com/tensorflow/models","n_code_links":234,"syntology":{"n_ran":11,"n_unverified":0,"n_samples":11,"n_pointer_only_licence":6}},{"rank_in_archive_order":11,"model":"OLTR(ResNet-50)","metrics":{"Average mAP":"71.02"},"uses_additional_data":false,"paper_date":"2019-04-10","paper":"/paper/large-scale-long-tailed-recognition-in-an","paper_url":"http://arxiv.org/abs/1904.05160v2","paper_title":"Large-Scale Long-Tailed Recognition in an Open World","code":"https://github.com/zhmiao/OpenLongTailRecognition-OLTR","n_code_links":2,"syntology":null},{"rank_in_archive_order":12,"model":"LDAM(ResNet-50)","metrics":{"Average mAP":"70.73"},"uses_additional_data":false,"paper_date":"2019-06-18","paper":"/paper/learning-imbalanced-datasets-with-label","paper_url":"https://arxiv.org/abs/1906.07413v2","paper_title":"Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss","code":"https://github.com/kaidic/LDAM-DRW","n_code_links":7,"syntology":{"n_ran":2,"n_unverified":9,"n_samples":11,"n_pointer_only_licence":3}},{"rank_in_archive_order":13,"model":"ML-GCN(ResNet-50)","metrics":{"Average mAP":"68.92"},"uses_additional_data":false,"paper_date":"2019-04-07","paper":"/paper/multi-label-image-recognition-with-graph","paper_url":"http://arxiv.org/abs/1904.03582v1","paper_title":"Multi-Label Image Recognition with Graph Convolutional Networks","code":"https://github.com/megvii-research/ml-gcn","n_code_links":2,"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 6,795 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":6795,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":2785},"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":7,"rows_with_any_sample_ran":5,"distinct_papers_with_graph_line":5,"distinct_papers_with_any_sample_ran":4,"samples_over_distinct_papers":{"n_ran":36,"n_unverified":42,"n_samples":78,"n_pointer_only_licence":25,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":52,"n_unverified":55,"n_samples":107,"n_pointer_only_licence":41,"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"}}}