{"url":"/sota/long-tail-learning-on-imagenet-lt","task":{"name":"Long-tail Learning","url":"/task/long-tail-learning","note":null},"dataset":{"name":"ImageNet-LT","url":"/dataset/imagenet-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"],"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"}},"counts":{"rows":69,"rows_with_code":64,"rows_with_paper_page":69,"rows_dated":69,"rows_using_additional_data":3},"rows":[{"rank_in_archive_order":1,"model":"LIFT (ViT-L/14)","metrics":{"Top-1 Accuracy":"82.9"},"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":"µ2Net+ (ViT-L/16)","metrics":{"Top-1 Accuracy":"82.5"},"uses_additional_data":false,"paper_date":"2022-09-15","paper":"/paper/a-continual-development-methodology-for-large","paper_url":"https://arxiv.org/abs/2209.07326v3","paper_title":"A Continual Development Methodology for Large-scale Multitask Dynamic ML Systems","code":"https://github.com/google-research/google-research/tree/master/muNet","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"MAM (ViT-B/16)","metrics":{"Top-1 Accuracy":"82.3"},"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":"LIFT (ViT-B/16)","metrics":{"Top-1 Accuracy":"78.3"},"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":5,"model":"VL-LTR (ViT-B-16)","metrics":{"Top-1 Accuracy":"77.2"},"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":6,"model":"BALLAD(ResNet-50×16)","metrics":{"Top-1 Accuracy":"76.5"},"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":7,"model":"BALLAD(ViT-B-16)","metrics":{"Top-1 Accuracy":"75.7"},"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":8,"model":"BALLAD(ResNet-101)","metrics":{"Top-1 Accuracy":"70.5"},"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":9,"model":"VL-LTR (ResNet-50)","metrics":{"Top-1 Accuracy":"70.1"},"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":10,"model":"BALLAD(ResNet-50)","metrics":{"Top-1 Accuracy":"67.2"},"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":"GPaCo (2-ResNeXt101-32x4d)","metrics":{"Top-1 Accuracy":"63.2"},"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":12,"model":"MDCS (ResNeXt-50)","metrics":{"Top-1 Accuracy":"61.8"},"uses_additional_data":false,"paper_date":"2023-08-19","paper":"/paper/mdcs-more-diverse-experts-with-consistency","paper_url":"https://arxiv.org/abs/2308.09922v2","paper_title":"MDCS: More Diverse Experts with Consistency Self-distillation for Long-tailed Recognition","code":"https://github.com/fistyee/mdcs","n_code_links":1,"syntology":{"n_ran":7,"n_unverified":1,"n_samples":8,"n_pointer_only_licence":8}},{"rank_in_archive_order":13,"model":"TADE(ResNeXt101-32x4d)","metrics":{"Top-1 Accuracy":"61.4"},"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":14,"model":"ProCo (ResNet50)","metrics":{"Top-1 Accuracy":"60.2"},"uses_additional_data":false,"paper_date":"2024-03-11","paper":"/paper/probabilistic-contrastive-learning-for-long","paper_url":"https://arxiv.org/abs/2403.06726v2","paper_title":"Probabilistic Contrastive Learning for Long-Tailed Visual Recognition","code":"https://github.com/leaplabthu/proco","n_code_links":1,"syntology":{"n_ran":6,"n_unverified":3,"n_samples":9,"n_pointer_only_licence":0}},{"rank_in_archive_order":15,"model":"PaCo(ResNeXt101-32x4d)","metrics":{"Top-1 Accuracy":"60.0"},"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":16,"model":"DeiT-LT","metrics":{"Top-1 Accuracy":"59.1"},"uses_additional_data":false,"paper_date":"2024-04-03","paper":"/paper/deit-lt-distillation-strikes-back-for-vision","paper_url":"https://arxiv.org/abs/2404.02900v1","paper_title":"DeiT-LT Distillation Strikes Back for Vision Transformer Training on Long-Tailed Datasets","code":"https://github.com/val-iisc/DeiT-LT","n_code_links":2,"syntology":null},{"rank_in_archive_order":17,"model":"APA (SE-ResNext-50)","metrics":{"Top-1 Accuracy":"59.1"},"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":18,"model":"TADE(ResNeXt-50)","metrics":{"Top-1 Accuracy":"58.8"},"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":19,"model":"GML (ResNeXt-50)","metrics":{"Top-1 Accuracy":"58.8"},"uses_additional_data":false,"paper_date":"2023-05-02","paper":"/paper/long-tailed-recognition-by-mutual-information","paper_url":"https://arxiv.org/abs/2305.01160v3","paper_title":"Long-Tailed Recognition by Mutual Information Maximization between Latent Features and Ground-Truth Labels","code":"https://github.com/bluecdm/Long-tailed-recognition","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":"DirMixE(ResNeXt-50)","metrics":{"Top-1 Accuracy":"58.61"},"uses_additional_data":false,"paper_date":"2024-05-13","paper":"/paper/harnessing-hierarchical-label-distribution","paper_url":"https://arxiv.org/abs/2405.07780v1","paper_title":"Harnessing Hierarchical Label Distribution Variations in Test Agnostic Long-tail Recognition","code":"https://github.com/scongl/dirmixe","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":21,"model":"NCL(ResNeXt-50)","metrics":{"Top-1 Accuracy":"58.4"},"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":22,"model":"PaCo(ResNeXt-50)","metrics":{"Top-1 Accuracy":"58.2"},"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":23,"model":"BS-CMO (ResNet-50)","metrics":{"Top-1 Accuracy":"58.0"},"uses_additional_data":false,"paper_date":"2021-12-01","paper":"/paper/the-majority-can-help-the-minority-context","paper_url":"https://arxiv.org/abs/2112.00412v3","paper_title":"The Majority Can Help The Minority: Context-rich Minority Oversampling for Long-tailed Classification","code":"https://github.com/naver-ai/cmo","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":2,"n_samples":5,"n_pointer_only_licence":2}},{"rank_in_archive_order":24,"model":"ProCo (ResNeXt50)","metrics":{"Top-1 Accuracy":"58.0"},"uses_additional_data":false,"paper_date":"2024-03-11","paper":"/paper/probabilistic-contrastive-learning-for-long","paper_url":"https://arxiv.org/abs/2403.06726v2","paper_title":"Probabilistic Contrastive Learning for Long-Tailed Visual Recognition","code":"https://github.com/leaplabthu/proco","n_code_links":1,"syntology":{"n_ran":6,"n_unverified":3,"n_samples":9,"n_pointer_only_licence":0}},{"rank_in_archive_order":25,"model":"APA (SE-ResNet-50)","metrics":{"Top-1 Accuracy":"57.9"},"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":26,"model":"CBD-ENS (ResNet-152)","metrics":{"Top-1 Accuracy":"57.7"},"uses_additional_data":false,"paper_date":"2021-04-12","paper":"/paper/class-balanced-distillation-for-long-tailed","paper_url":"https://arxiv.org/abs/2104.05279v2","paper_title":"Class-Balanced Distillation for Long-Tailed Visual Recognition","code":"https://github.com/google-research/google-research","n_code_links":3,"syntology":null},{"rank_in_archive_order":27,"model":"ResLT(ResNeXt-50-3 experts)","metrics":{"Top-1 Accuracy":"57.6"},"uses_additional_data":false,"paper_date":"2021-01-26","paper":"/paper/reslt-residual-learning-for-long-tailed","paper_url":"https://arxiv.org/abs/2101.10633v3","paper_title":"ResLT: Residual Learning for Long-tailed Recognition","code":"https://github.com/dvlab-research/parametric-contrastive-learning","n_code_links":5,"syntology":{"n_ran":5,"n_unverified":4,"n_samples":9,"n_pointer_only_licence":1}},{"rank_in_archive_order":28,"model":"BatchFormer(ResNet-50, PaCo)","metrics":{"Top-1 Accuracy":"57.4"},"uses_additional_data":false,"paper_date":"2022-03-03","paper":"/paper/batchformer-learning-to-explore-sample","paper_url":"https://arxiv.org/abs/2203.01522v2","paper_title":"BatchFormer: Learning to Explore Sample Relationships for Robust Representation Learning","code":"https://github.com/zhihou7/batchformer","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":29,"model":"NCL(ResNet-50)","metrics":{"Top-1 Accuracy":"57.4"},"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":30,"model":"Difficulty-Net (ResNet-50 using RandAugment, single model)","metrics":{"Top-1 Accuracy":"57.4"},"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":31,"model":"RIDE-DiVE","metrics":{"Top-1 Accuracy":"57.12"},"uses_additional_data":false,"paper_date":"2021-03-28","paper":"/paper/distilling-virtual-examples-for-long-tailed","paper_url":"https://arxiv.org/abs/2103.15042v3","paper_title":"Distilling Virtual Examples for Long-tailed Recognition","code":"https://github.com/yangyucheng000/DiVE","n_code_links":1,"syntology":null},{"rank_in_archive_order":32,"model":"BCL(ResNeXt-50)","metrics":{"Top-1 Accuracy":"57.1"},"uses_additional_data":false,"paper_date":"2022-07-19","paper":"/paper/balanced-contrastive-learning-for-long-tailed-1","paper_url":"https://arxiv.org/abs/2207.09052v3","paper_title":"Balanced Contrastive Learning for Long-Tailed Visual Recognition","code":"https://github.com/flamiezhu/bcl","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":33,"model":"RIDE (ResNeXt-50)","metrics":{"Top-1 Accuracy":"56.4"},"uses_additional_data":false,"paper_date":"2020-10-05","paper":"/paper/long-tailed-recognition-by-routing-diverse-1","paper_url":"https://arxiv.org/abs/2010.01809v4","paper_title":"Long-tailed Recognition by Routing Diverse Distribution-Aware Experts","code":"https://github.com/frank-xwang/RIDE-LongTailRecognition","n_code_links":2,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":34,"model":"GLMC (ResNeXt-50)","metrics":{"Top-1 Accuracy":"56.3"},"uses_additional_data":false,"paper_date":"2023-05-15","paper":"/paper/global-and-local-mixture-consistency-1","paper_url":"https://arxiv.org/abs/2305.08661v1","paper_title":"Global and Local Mixture Consistency Cumulative Learning for Long-tailed Visual Recognitions","code":"https://github.com/ynu-yangpeng/GLMC","n_code_links":2,"syntology":{"n_ran":7,"n_unverified":3,"n_samples":10,"n_pointer_only_licence":5}},{"rank_in_archive_order":35,"model":"BatchFormer(ResNet-50, RIDE)","metrics":{"Top-1 Accuracy":"55.7"},"uses_additional_data":false,"paper_date":"2022-03-03","paper":"/paper/batchformer-learning-to-explore-sample","paper_url":"https://arxiv.org/abs/2203.01522v2","paper_title":"BatchFormer: Learning to Explore Sample Relationships for Robust Representation Learning","code":"https://github.com/zhihou7/batchformer","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":36,"model":"CBD-ENS (ResNet-50)","metrics":{"Top-1 Accuracy":"55.6"},"uses_additional_data":false,"paper_date":"2021-04-12","paper":"/paper/class-balanced-distillation-for-long-tailed","paper_url":"https://arxiv.org/abs/2104.05279v2","paper_title":"Class-Balanced Distillation for Long-Tailed Visual Recognition","code":"https://github.com/google-research/google-research","n_code_links":3,"syntology":null},{"rank_in_archive_order":37,"model":"ResLT(ResNeXt101-32x4d)","metrics":{"Top-1 Accuracy":"55.1"},"uses_additional_data":false,"paper_date":"2021-01-26","paper":"/paper/reslt-residual-learning-for-long-tailed","paper_url":"https://arxiv.org/abs/2101.10633v3","paper_title":"ResLT: Residual Learning for Long-tailed Recognition","code":"https://github.com/dvlab-research/parametric-contrastive-learning","n_code_links":5,"syntology":{"n_ran":5,"n_unverified":4,"n_samples":9,"n_pointer_only_licence":1}},{"rank_in_archive_order":38,"model":"OPeN (ResNeXt-50)","metrics":{"Top-1 Accuracy":"55.1"},"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":39,"model":"RIDE (ResNet-50)","metrics":{"Top-1 Accuracy":"54.9"},"uses_additional_data":false,"paper_date":"2020-10-05","paper":"/paper/long-tailed-recognition-by-routing-diverse-1","paper_url":"https://arxiv.org/abs/2010.01809v4","paper_title":"Long-tailed Recognition by Routing Diverse Distribution-Aware Experts","code":"https://github.com/frank-xwang/RIDE-LongTailRecognition","n_code_links":2,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":40,"model":"Difficulty-Net (ResNet-50 w/o using RandAugment, single model)","metrics":{"Top-1 Accuracy":"54.0"},"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":41,"model":"LTR-weight-balancing(ResNeXt-50)","metrics":{"Top-1 Accuracy":"53.9"},"uses_additional_data":false,"paper_date":"2022-03-27","paper":"/paper/long-tailed-recognition-via-weight-balancing","paper_url":"https://arxiv.org/abs/2203.14197v1","paper_title":"Long-Tailed Recognition via Weight Balancing","code":"https://github.com/shadealsha/ltr-weight-balancing","n_code_links":2,"syntology":{"n_ran":5,"n_unverified":9,"n_samples":14,"n_pointer_only_licence":13}},{"rank_in_archive_order":42,"model":"DRO-LT","metrics":{"Top-1 Accuracy":"53.5"},"uses_additional_data":false,"paper_date":"2021-04-07","paper":"/paper/distributional-robustness-loss-for-long-tail","paper_url":"https://arxiv.org/abs/2104.03066v2","paper_title":"Distributional Robustness Loss for Long-tail Learning","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":43,"model":"DisAlign","metrics":{"Top-1 Accuracy":"53.4"},"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":1,"n_unverified":2,"n_samples":3,"n_pointer_only_licence":3}},{"rank_in_archive_order":44,"model":"DiVE","metrics":{"Top-1 Accuracy":"53.1"},"uses_additional_data":false,"paper_date":"2021-03-28","paper":"/paper/distilling-virtual-examples-for-long-tailed","paper_url":"https://arxiv.org/abs/2103.15042v3","paper_title":"Distilling Virtual Examples for Long-tailed Recognition","code":"https://github.com/yangyucheng000/DiVE","n_code_links":1,"syntology":null},{"rank_in_archive_order":45,"model":"LDAM + DRW + SAM","metrics":{"Top-1 Accuracy":"53.1"},"uses_additional_data":false,"paper_date":"2022-12-28","paper":"/paper/escaping-saddle-points-for-effective","paper_url":"https://arxiv.org/abs/2212.13827v1","paper_title":"Escaping Saddle Points for Effective Generalization on Class-Imbalanced Data","code":"https://github.com/val-iisc/saddle-longtail","n_code_links":1,"syntology":null},{"rank_in_archive_order":46,"model":"LADE","metrics":{"Top-1 Accuracy":"53.0"},"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":47,"model":"ResLT(ResNeXt50)","metrics":{"Top-1 Accuracy":"52.9"},"uses_additional_data":false,"paper_date":"2021-01-26","paper":"/paper/reslt-residual-learning-for-long-tailed","paper_url":"https://arxiv.org/abs/2101.10633v3","paper_title":"ResLT: Residual Learning for Long-tailed Recognition","code":"https://github.com/dvlab-research/parametric-contrastive-learning","n_code_links":5,"syntology":{"n_ran":5,"n_unverified":4,"n_samples":9,"n_pointer_only_licence":1}},{"rank_in_archive_order":48,"model":"MiSLAS","metrics":{"Top-1 Accuracy":"52.7"},"uses_additional_data":false,"paper_date":"2021-04-01","paper":"/paper/improving-calibration-for-long-tailed-1","paper_url":"https://arxiv.org/abs/2104.00466v1","paper_title":"Improving Calibration for Long-Tailed Recognition","code":"https://github.com/Jia-Research-Lab/MiSLAS","n_code_links":5,"syntology":{"n_ran":5,"n_unverified":4,"n_samples":9,"n_pointer_only_licence":0}},{"rank_in_archive_order":49,"model":"TSC(ResNet-50)","metrics":{"Top-1 Accuracy":"52.4"},"uses_additional_data":false,"paper_date":"2021-11-27","paper":"/paper/targeted-supervised-contrastive-learning-for","paper_url":"https://arxiv.org/abs/2111.13998v2","paper_title":"Targeted Supervised Contrastive Learning for Long-Tailed Recognition","code":"https://github.com/lth14/targeted-supcon","n_code_links":1,"syntology":{"n_ran":6,"n_unverified":8,"n_samples":14,"n_pointer_only_licence":0}},{"rank_in_archive_order":50,"model":"LDAM-DRS-RSG","metrics":{"Top-1 Accuracy":"51.8"},"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":51,"model":"De-confound-TDE","metrics":{"Top-1 Accuracy":"51.8"},"uses_additional_data":false,"paper_date":"2020-09-28","paper":"/paper/long-tailed-classification-by-keeping-the-1","paper_url":"https://arxiv.org/abs/2009.12991v4","paper_title":"Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effect","code":"https://github.com/KaihuaTang/Long-Tailed-Recognition.pytorch","n_code_links":2,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":52,"model":"KCL","metrics":{"Top-1 Accuracy":"51.5"},"uses_additional_data":false,"paper_date":"2021-01-01","paper":"/paper/exploring-balanced-feature-spaces-for","paper_url":"https://openreview.net/forum?id=OqtLIabPTit","paper_title":"Exploring Balanced Feature Spaces for Representation Learning","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":53,"model":"cRT + SSP","metrics":{"Top-1 Accuracy":"51.3"},"uses_additional_data":false,"paper_date":"2020-06-13","paper":"/paper/rethinking-the-value-of-labels-for-improving","paper_url":"https://arxiv.org/abs/2006.07529v2","paper_title":"Rethinking the Value of Labels for Improving Class-Imbalanced Learning","code":"https://github.com/YyzHarry/imbalanced-semi-self","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":54,"model":"Logit adjustment","metrics":{"Top-1 Accuracy":"51.3"},"uses_additional_data":false,"paper_date":"2020-07-14","paper":"/paper/long-tail-learning-via-logit-adjustment","paper_url":"https://arxiv.org/abs/2007.07314v2","paper_title":"Long-tail learning via logit adjustment","code":"https://github.com/google-research/google-research/tree/master/logit_adjustment","n_code_links":3,"syntology":{"n_ran":7,"n_unverified":0,"n_samples":7,"n_pointer_only_licence":1}},{"rank_in_archive_order":55,"model":"MetaSAug (ResNet-152)","metrics":{"Top-1 Accuracy":"50.03"},"uses_additional_data":false,"paper_date":"2021-03-23","paper":"/paper/metasaug-meta-semantic-augmentation-for-long","paper_url":"https://arxiv.org/abs/2103.12579v3","paper_title":"MetaSAug: Meta Semantic Augmentation for Long-Tailed Visual Recognition","code":"https://github.com/BIT-DA/MetaSAug","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":1,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":56,"model":"MetaSAug with CE loss","metrics":{"Top-1 Accuracy":"47.39"},"uses_additional_data":false,"paper_date":"2021-03-23","paper":"/paper/metasaug-meta-semantic-augmentation-for-long","paper_url":"https://arxiv.org/abs/2103.12579v3","paper_title":"MetaSAug: Meta Semantic Augmentation for Long-Tailed Visual Recognition","code":"https://github.com/BIT-DA/MetaSAug","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":1,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":57,"model":"BLT (DenseNet-121)","metrics":{"Top-1 Accuracy":"44.7"},"uses_additional_data":false,"paper_date":"2020-10-30","paper":"/paper/blt-balancing-long-tailed-datasets-with","paper_url":"https://openaccess.thecvf.com/content/ACCV2020/papers/Kozerawski_BLT_Balancing_Long-Tailed_Datasets_with_Adversarially-Perturbed_Images_ACCV_2020_paper.pdf","paper_title":"BLT: Balancing Long-Tailed Datasets with Adversarially-Perturbed Images","code":"https://github.com/JKozerawski/BLT","n_code_links":1,"syntology":null},{"rank_in_archive_order":58,"model":"Difficulty-Net (ResNet-10 w/o using RandAugment, single model","metrics":{"Top-1 Accuracy":"44.6"},"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":59,"model":"IEM","metrics":{"Top-1 Accuracy":"43.2"},"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":60,"model":"smDRAGON","metrics":{"Top-1 Accuracy":"42.0"},"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":61,"model":"BALMS","metrics":{"Top-1 Accuracy":"41.8"},"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":62,"model":"CB LWS","metrics":{"Top-1 Accuracy":"41.4"},"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":63,"model":"CBExperts","metrics":{"Top-1 Accuracy":"39.2"},"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":2,"n_unverified":7,"n_samples":9,"n_pointer_only_licence":0}},{"rank_in_archive_order":64,"model":"LFME + OLTR","metrics":{"Top-1 Accuracy":"38.8"},"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":65,"model":"CDB-loss (ResNet 10)","metrics":{"Top-1 Accuracy":"38.5"},"uses_additional_data":false,"paper_date":"2020-10-05","paper":"/paper/class-wise-difficulty-balanced-loss-for","paper_url":"https://arxiv.org/abs/2010.01824v1","paper_title":"Class-Wise Difficulty-Balanced Loss for Solving Class-Imbalance","code":"https://github.com/hitachi-rd-cv/CDB-loss","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":2,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":66,"model":"BLT (ResNet-10)","metrics":{"Top-1 Accuracy":"38.0"},"uses_additional_data":false,"paper_date":"2020-10-30","paper":"/paper/blt-balancing-long-tailed-datasets-with","paper_url":"https://openaccess.thecvf.com/content/ACCV2020/papers/Kozerawski_BLT_Balancing_Long-Tailed_Datasets_with_Adversarially-Perturbed_Images_ACCV_2020_paper.pdf","paper_title":"BLT: Balancing Long-Tailed Datasets with Adversarially-Perturbed Images","code":"https://github.com/JKozerawski/BLT","n_code_links":1,"syntology":null},{"rank_in_archive_order":67,"model":"OLTR","metrics":{"Top-1 Accuracy":"35.6"},"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":68,"model":"Online Feature Augmentation","metrics":{"Top-1 Accuracy":"35.3"},"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":69,"model":"Domain Adaptation","metrics":{"Top-1 Accuracy":"29.9"},"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":2,"n_unverified":1,"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 6,821 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":38,"rows_with_any_sample_ran":36,"distinct_papers_with_graph_line":28,"distinct_papers_with_any_sample_ran":26,"samples_over_distinct_papers":{"n_ran":83,"n_unverified":55,"n_samples":138,"n_pointer_only_licence":53,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":116,"n_unverified":74,"n_samples":190,"n_pointer_only_licence":66,"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"}}}