{"url":"/sota/long-tail-learning-on-places-lt","task":{"name":"Long-tail Learning","url":"/task/long-tail-learning","note":null},"dataset":{"name":"Places-LT","url":"/dataset/places-lt"},"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":["Top-1 Accuracy","Top 1 Accuracy"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Top-1 Accuracy":"higher","Top 1 Accuracy":"higher"}},"counts":{"rows":29,"rows_with_code":25,"rows_with_paper_page":29,"rows_dated":29,"rows_using_additional_data":6},"rows":[{"rank_in_archive_order":1,"model":"LIFT (ViT-L/14)","metrics":{"Top-1 Accuracy":"53.7"},"uses_additional_data":false,"paper_date":"2023-09-18","paper":"/paper/parameter-efficient-long-tailed-recognition","paper_url":"https://arxiv.org/abs/2309.10019v3","paper_title":"Long-Tail Learning with Foundation Model: Heavy Fine-Tuning Hurts","code":"https://github.com/shijxcs/lift","n_code_links":1,"syntology":{"n_ran":5,"n_unverified":3,"n_samples":8,"n_pointer_only_licence":8}},{"rank_in_archive_order":2,"model":"LIFT (ViT-B/16)","metrics":{"Top-1 Accuracy":"52.2"},"uses_additional_data":false,"paper_date":"2023-09-18","paper":"/paper/parameter-efficient-long-tailed-recognition","paper_url":"https://arxiv.org/abs/2309.10019v3","paper_title":"Long-Tail Learning with Foundation Model: Heavy Fine-Tuning Hurts","code":"https://github.com/shijxcs/lift","n_code_links":1,"syntology":{"n_ran":5,"n_unverified":3,"n_samples":8,"n_pointer_only_licence":8}},{"rank_in_archive_order":3,"model":"MAM (ViT-B/16)","metrics":{"Top-1 Accuracy":"51.4"},"uses_additional_data":true,"paper_date":"2023-04-11","paper":"/paper/improving-image-recognition-by-retrieving","paper_url":"https://arxiv.org/abs/2304.05173v1","paper_title":"Improving Image Recognition by Retrieving from Web-Scale Image-Text Data","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":4,"model":"VL-LTR (ViT-B-16)","metrics":{"Top-1 Accuracy":"50.1"},"uses_additional_data":true,"paper_date":"2021-11-26","paper":"/paper/vl-ltr-learning-class-wise-visual-linguistic","paper_url":"https://arxiv.org/abs/2111.13579v4","paper_title":"VL-LTR: Learning Class-wise Visual-Linguistic Representation for Long-Tailed Visual Recognition","code":"https://github.com/ChangyaoTian/VL-LTR","n_code_links":1,"syntology":null},{"rank_in_archive_order":5,"model":"BALLAD(ViT-B-16)","metrics":{"Top-1 Accuracy":"49.5"},"uses_additional_data":true,"paper_date":"2021-11-29","paper":"/paper/a-simple-long-tailed-recognition-baseline-via","paper_url":"https://arxiv.org/abs/2111.14745v1","paper_title":"A Simple Long-Tailed Recognition Baseline via Vision-Language Model","code":"https://github.com/gaopengcuhk/ballad","n_code_links":1,"syntology":null},{"rank_in_archive_order":6,"model":"BALLAD(ResNet-50×16)","metrics":{"Top-1 Accuracy":"49.3"},"uses_additional_data":true,"paper_date":"2021-11-29","paper":"/paper/a-simple-long-tailed-recognition-baseline-via","paper_url":"https://arxiv.org/abs/2111.14745v1","paper_title":"A Simple Long-Tailed Recognition Baseline via Vision-Language Model","code":"https://github.com/gaopengcuhk/ballad","n_code_links":1,"syntology":null},{"rank_in_archive_order":7,"model":"VL-LTR (ResNet-50)","metrics":{"Top-1 Accuracy":"48.0"},"uses_additional_data":true,"paper_date":"2021-11-26","paper":"/paper/vl-ltr-learning-class-wise-visual-linguistic","paper_url":"https://arxiv.org/abs/2111.13579v4","paper_title":"VL-LTR: Learning Class-wise Visual-Linguistic Representation for Long-Tailed Visual Recognition","code":"https://github.com/ChangyaoTian/VL-LTR","n_code_links":1,"syntology":null},{"rank_in_archive_order":8,"model":"BALLAD(ResNet-101)","metrics":{"Top-1 Accuracy":"47.9"},"uses_additional_data":true,"paper_date":"2021-11-29","paper":"/paper/a-simple-long-tailed-recognition-baseline-via","paper_url":"https://arxiv.org/abs/2111.14745v1","paper_title":"A Simple Long-Tailed Recognition Baseline via Vision-Language Model","code":"https://github.com/gaopengcuhk/ballad","n_code_links":1,"syntology":null},{"rank_in_archive_order":9,"model":"RAC (ViT-B-16)","metrics":{"Top-1 Accuracy":"47.17"},"uses_additional_data":false,"paper_date":"2022-02-22","paper":"/paper/retrieval-augmented-classification-for-long","paper_url":"https://arxiv.org/abs/2202.11233v1","paper_title":"Retrieval Augmented Classification for Long-Tail Visual Recognition","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":10,"model":"BALLAD(ResNet-50)","metrics":{"Top-1 Accuracy":"46.5"},"uses_additional_data":false,"paper_date":"2021-11-29","paper":"/paper/a-simple-long-tailed-recognition-baseline-via","paper_url":"https://arxiv.org/abs/2111.14745v1","paper_title":"A Simple Long-Tailed Recognition Baseline via Vision-Language Model","code":"https://github.com/gaopengcuhk/ballad","n_code_links":1,"syntology":null},{"rank_in_archive_order":11,"model":"APA (SE-ResNet-50)","metrics":{"Top-1 Accuracy":"42.0"},"uses_additional_data":false,"paper_date":"2024-07-11","paper":"/paper/adaptive-parametric-activation","paper_url":"https://arxiv.org/abs/2407.08567v2","paper_title":"Adaptive Parametric Activation","code":"https://github.com/kostas1515/aglu","n_code_links":1,"syntology":null},{"rank_in_archive_order":12,"model":"Difficulty-Net (ResNet-152)","metrics":{"Top-1 Accuracy":"41.7"},"uses_additional_data":false,"paper_date":"2022-09-07","paper":"/paper/difficulty-net-learning-to-predict-difficulty","paper_url":"https://arxiv.org/abs/2209.02960v1","paper_title":"Difficulty-Net: Learning to Predict Difficulty for Long-Tailed Recognition","code":"https://github.com/hitachi-rd-cv/Difficulty_Net","n_code_links":1,"syntology":null},{"rank_in_archive_order":13,"model":"GPaCo (ResNet-152)","metrics":{"Top-1 Accuracy":"41.7"},"uses_additional_data":false,"paper_date":"2022-09-26","paper":"/paper/generalized-parametric-contrastive-learning","paper_url":"https://arxiv.org/abs/2209.12400v2","paper_title":"Generalized Parametric Contrastive Learning","code":"https://github.com/dvlab-research/parametric-contrastive-learning","n_code_links":4,"syntology":null},{"rank_in_archive_order":14,"model":"NCL(ResNet-152)","metrics":{"Top-1 Accuracy":"41.5"},"uses_additional_data":false,"paper_date":"2022-03-29","paper":"/paper/nested-collaborative-learning-for-long-tailed","paper_url":"https://arxiv.org/abs/2203.15359v2","paper_title":"Nested Collaborative Learning for Long-Tailed Visual Recognition","code":"https://github.com/bazinga699/ncl","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":15,"model":"TADE","metrics":{"Top 1 Accuracy":"40.9","Top-1 Accuracy":"41.3"},"uses_additional_data":false,"paper_date":"2021-07-20","paper":"/paper/test-agnostic-long-tailed-recognition-by-test","paper_url":"https://arxiv.org/abs/2107.09249v4","paper_title":"Self-Supervised Aggregation of Diverse Experts for Test-Agnostic Long-Tailed Recognition","code":"https://github.com/vanint/sade-agnosticlt","n_code_links":2,"syntology":{"n_ran":4,"n_unverified":2,"n_samples":6,"n_pointer_only_licence":0}},{"rank_in_archive_order":16,"model":"PaCo","metrics":{"Top-1 Accuracy":"41.2"},"uses_additional_data":false,"paper_date":"2021-07-26","paper":"/paper/parametric-contrastive-learning","paper_url":"https://arxiv.org/abs/2107.12028v2","paper_title":"Parametric Contrastive Learning","code":"https://github.com/dvlab-research/parametric-contrastive-learning","n_code_links":5,"syntology":{"n_ran":1,"n_unverified":2,"n_samples":3,"n_pointer_only_licence":1}},{"rank_in_archive_order":17,"model":"OPeN (ResNet-152)","metrics":{"Top-1 Accuracy":"40.5"},"uses_additional_data":false,"paper_date":"2021-12-16","paper":"/paper/pure-noise-to-the-rescue-of-insufficient-data","paper_url":"https://arxiv.org/abs/2112.08810v2","paper_title":"Pure Noise to the Rescue of Insufficient Data: Improving Imbalanced Classification by Training on Random Noise Images","code":"https://github.com/shiranzada/pure-noise","n_code_links":1,"syntology":null},{"rank_in_archive_order":18,"model":"IEM","metrics":{"Top-1 Accuracy":"39.7"},"uses_additional_data":false,"paper_date":"2020-06-01","paper":"/paper/inflated-episodic-memory-with-region-self","paper_url":"http://openaccess.thecvf.com/content_CVPR_2020/html/Zhu_Inflated_Episodic_Memory_With_Region_Self-Attention_for_Long-Tailed_Visual_Recognition_CVPR_2020_paper.html","paper_title":"Inflated Episodic Memory With Region Self-Attention for Long-Tailed Visual Recognition","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":19,"model":"LDAM-DRS-RSG","metrics":{"Top-1 Accuracy":"39.3"},"uses_additional_data":false,"paper_date":"2021-06-18","paper":"/paper/rsg-a-simple-but-effective-module-for","paper_url":"https://arxiv.org/abs/2106.09859v1","paper_title":"RSG: A Simple but Effective Module for Learning Imbalanced Datasets","code":"https://github.com/Jianf-Wang/RSG","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":20,"model":"DisAlign","metrics":{"Top-1 Accuracy":"39.3"},"uses_additional_data":false,"paper_date":"2021-03-30","paper":"/paper/distribution-alignment-a-unified-framework","paper_url":"https://arxiv.org/abs/2103.16370v1","paper_title":"Distribution Alignment: A Unified Framework for Long-tail Visual Recognition","code":"https://github.com/Megvii-BaseDetection/DisAlign","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":3,"n_samples":3,"n_pointer_only_licence":3}},{"rank_in_archive_order":21,"model":"CBExperts","metrics":{"Top-1 Accuracy":"38.9"},"uses_additional_data":false,"paper_date":"2020-04-07","paper":"/paper/long-tailed-recognition-using-class-balanced","paper_url":"https://arxiv.org/abs/2004.03706v2","paper_title":"Long-Tailed Recognition Using Class-Balanced Experts","code":"https://github.com/ssfootball04/class-balanced-experts","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":8,"n_samples":9,"n_pointer_only_licence":0}},{"rank_in_archive_order":22,"model":"LADE","metrics":{"Top-1 Accuracy":"38.8"},"uses_additional_data":false,"paper_date":"2020-12-01","paper":"/paper/disentangling-label-distribution-for-long","paper_url":"https://arxiv.org/abs/2012.00321v2","paper_title":"Disentangling Label Distribution for Long-tailed Visual Recognition","code":"https://github.com/hyperconnect/LADE","n_code_links":2,"syntology":null},{"rank_in_archive_order":23,"model":"BALMS","metrics":{"Top-1 Accuracy":"38.7"},"uses_additional_data":false,"paper_date":"2020-07-21","paper":"/paper/balanced-meta-softmax-for-long-tailed-visual","paper_url":"https://arxiv.org/abs/2007.10740v3","paper_title":"Balanced Meta-Softmax for Long-Tailed Visual Recognition","code":"https://github.com/jiawei-ren/BalancedMetaSoftmax","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":24,"model":"smDRAGON","metrics":{"Top-1 Accuracy":"38.1"},"uses_additional_data":false,"paper_date":"2020-04-05","paper":"/paper/long-tail-learning-with-attributes","paper_url":"https://arxiv.org/abs/2004.02235v4","paper_title":"From Generalized zero-shot learning to long-tail with class descriptors","code":"https://github.com/dvirsamuel/DRAGON","n_code_links":1,"syntology":null},{"rank_in_archive_order":25,"model":"CB LWS","metrics":{"Top-1 Accuracy":"37.6"},"uses_additional_data":false,"paper_date":"2019-10-21","paper":"/paper/decoupling-representation-and-classifier-for","paper_url":"https://arxiv.org/abs/1910.09217v2","paper_title":"Decoupling Representation and Classifier for Long-Tailed Recognition","code":"https://github.com/facebookresearch/classifier-balancing","n_code_links":4,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":26,"model":"Online Feature Augmentation","metrics":{"Top-1 Accuracy":"36.4"},"uses_additional_data":false,"paper_date":"2020-08-09","paper":"/paper/feature-space-augmentation-for-long-tailed","paper_url":"https://arxiv.org/abs/2008.03673v1","paper_title":"Feature Space Augmentation for Long-Tailed Data","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":27,"model":"LFME + OLTR","metrics":{"Top-1 Accuracy":"36.2"},"uses_additional_data":false,"paper_date":"2020-01-06","paper":"/paper/learning-from-multiple-experts-self-paced","paper_url":"https://arxiv.org/abs/2001.01536v3","paper_title":"Learning From Multiple Experts: Self-paced Knowledge Distillation for Long-tailed Classification","code":"https://github.com/xiangly55/LFME","n_code_links":1,"syntology":null},{"rank_in_archive_order":28,"model":"OLTR","metrics":{"Top-1 Accuracy":"34.1"},"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":29,"model":"Domain Adaptation","metrics":{"Top-1 Accuracy":"30.8"},"uses_additional_data":false,"paper_date":"2020-03-24","paper":"/paper/rethinking-class-balanced-methods-for-long","paper_url":"https://arxiv.org/abs/2003.10780v1","paper_title":"Rethinking Class-Balanced Methods for Long-Tailed Visual Recognition from a Domain Adaptation Perspective","code":"https://github.com/abdullahjamal/Longtail_DA","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":2,"n_samples":3,"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 6,795 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":11,"rows_with_any_sample_ran":10,"distinct_papers_with_graph_line":10,"distinct_papers_with_any_sample_ran":9,"samples_over_distinct_papers":{"n_ran":19,"n_unverified":20,"n_samples":39,"n_pointer_only_licence":16,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":24,"n_unverified":23,"n_samples":47,"n_pointer_only_licence":24,"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"}}}