{"url":"/task/long-tail-learning","name":"Long-tail Learning","slug":"long-tail-learning","description_markdown":"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.","categories":[{"name":"Methodology","url":"/area/methodology"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":131,"papers_with_code":93,"benchmarks":20,"benchmark_tables_in_archive":20,"benchmark_tables_shown":20,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":16,"subtasks":1,"parent_tasks":2},"benchmarks":[{"leaderboard":"/sota/long-tail-learning-on-imagenet-lt","slug":"long-tail-learning-on-imagenet-lt","dataset":"ImageNet-LT","dataset_url":"/dataset/imagenet-lt","rows_in_archive":69,"metrics":["Top-1 Accuracy"],"first_row_in_archive_order":{"model":"LIFT (ViT-L/14)","paper_title":"Long-Tail Learning with Foundation Model: Heavy Fine-Tuning Hurts","paper_url":"/paper/parameter-efficient-long-tailed-recognition","paper_date":"2023-09-18","arxiv_id":"2309.10019","code_links":[{"title":"shijxcs/lift","url":"https://github.com/shijxcs/lift"}],"syntology":{"n":8,"n_ran":5,"n_unverified":3,"n_pointer_only":8}}},{"leaderboard":"/sota/long-tail-learning-on-cifar-100-lt-r-100","slug":"long-tail-learning-on-cifar-100-lt-r-100","dataset":"CIFAR-100-LT (ρ=100)","dataset_url":"/dataset/cifar-100","rows_in_archive":66,"metrics":["Error Rate"],"first_row_in_archive_order":{"model":"LPT","paper_title":"LPT: Long-tailed Prompt Tuning for Image Classification","paper_url":"/paper/lpt-long-tailed-prompt-tuning-for-image","paper_date":"2022-10-03","arxiv_id":"2210.01033","code_links":[{"title":"dongsky/lpt","url":"https://github.com/dongsky/lpt"}],"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}}},{"leaderboard":"/sota/long-tail-learning-on-cifar-10-lt-r-10","slug":"long-tail-learning-on-cifar-10-lt-r-10","dataset":"CIFAR-10-LT (ρ=10)","dataset_url":"/dataset/cifar-10","rows_in_archive":50,"metrics":["Error Rate"],"first_row_in_archive_order":{"model":"GLMC+MaxNorm (ResNet-34, channel x4)","paper_title":"Global and Local Mixture Consistency Cumulative Learning for Long-tailed Visual Recognitions","paper_url":"/paper/global-and-local-mixture-consistency-1","paper_date":"2023-05-15","arxiv_id":"2305.08661","code_links":[{"title":"ynu-yangpeng/GLMC","url":"https://github.com/ynu-yangpeng/GLMC"},{"title":"val-iisc/saddle-longtail","url":"https://github.com/val-iisc/saddle-longtail"}],"syntology":{"n":10,"n_ran":7,"n_unverified":3,"n_pointer_only":5}}},{"leaderboard":"/sota/long-tail-learning-on-inaturalist-2018","slug":"long-tail-learning-on-inaturalist-2018","dataset":"iNaturalist 2018","dataset_url":"/dataset/inaturalist","rows_in_archive":43,"metrics":["Top-1 Accuracy"],"first_row_in_archive_order":{"model":"LIFT (ViT-L/14@336px)","paper_title":"Long-Tail Learning with Foundation Model: Heavy Fine-Tuning Hurts","paper_url":"/paper/parameter-efficient-long-tailed-recognition","paper_date":"2023-09-18","arxiv_id":"2309.10019","code_links":[{"title":"shijxcs/lift","url":"https://github.com/shijxcs/lift"}],"syntology":{"n":8,"n_ran":5,"n_unverified":3,"n_pointer_only":8}}},{"leaderboard":"/sota/long-tail-learning-on-cifar-100-lt-r-10","slug":"long-tail-learning-on-cifar-100-lt-r-10","dataset":"CIFAR-100-LT (ρ=10)","dataset_url":"/dataset/cifar-100","rows_in_archive":31,"metrics":["Error Rate"],"first_row_in_archive_order":{"model":"LIFT (ViT-B/16, ImageNet-21K pre-training)","paper_title":"Long-Tail Learning with Foundation Model: Heavy Fine-Tuning Hurts","paper_url":"/paper/parameter-efficient-long-tailed-recognition","paper_date":"2023-09-18","arxiv_id":"2309.10019","code_links":[{"title":"shijxcs/lift","url":"https://github.com/shijxcs/lift"}],"syntology":{"n":8,"n_ran":5,"n_unverified":3,"n_pointer_only":8}}},{"leaderboard":"/sota/long-tail-learning-on-places-lt","slug":"long-tail-learning-on-places-lt","dataset":"Places-LT","dataset_url":"/dataset/places-lt","rows_in_archive":29,"metrics":["Top-1 Accuracy","Top 1 Accuracy"],"first_row_in_archive_order":{"model":"LIFT (ViT-L/14)","paper_title":"Long-Tail Learning with Foundation Model: Heavy Fine-Tuning Hurts","paper_url":"/paper/parameter-efficient-long-tailed-recognition","paper_date":"2023-09-18","arxiv_id":"2309.10019","code_links":[{"title":"shijxcs/lift","url":"https://github.com/shijxcs/lift"}],"syntology":{"n":8,"n_ran":5,"n_unverified":3,"n_pointer_only":8}}},{"leaderboard":"/sota/long-tail-learning-on-cifar-10-lt-r-100","slug":"long-tail-learning-on-cifar-10-lt-r-100","dataset":"CIFAR-10-LT (ρ=100)","dataset_url":"/dataset/cifar-10","rows_in_archive":28,"metrics":["Error Rate"],"first_row_in_archive_order":{"model":"GLMC+MaxNorm (ResNet-34, channel x4)","paper_title":"Global and Local Mixture Consistency Cumulative Learning for Long-tailed Visual Recognitions","paper_url":"/paper/global-and-local-mixture-consistency-1","paper_date":"2023-05-15","arxiv_id":"2305.08661","code_links":[{"title":"ynu-yangpeng/GLMC","url":"https://github.com/ynu-yangpeng/GLMC"},{"title":"val-iisc/saddle-longtail","url":"https://github.com/val-iisc/saddle-longtail"}],"syntology":{"n":10,"n_ran":7,"n_unverified":3,"n_pointer_only":5}}},{"leaderboard":"/sota/long-tail-learning-on-cifar-100-lt-r-50","slug":"long-tail-learning-on-cifar-100-lt-r-50","dataset":"CIFAR-100-LT (ρ=50)","dataset_url":null,"rows_in_archive":25,"metrics":["Error Rate"],"first_row_in_archive_order":{"model":"LIFT (ViT-B/16, ImageNet-21K pre-training)","paper_title":"Long-Tail Learning with Foundation Model: Heavy Fine-Tuning Hurts","paper_url":"/paper/parameter-efficient-long-tailed-recognition","paper_date":"2023-09-18","arxiv_id":"2309.10019","code_links":[{"title":"shijxcs/lift","url":"https://github.com/shijxcs/lift"}],"syntology":{"n":8,"n_ran":5,"n_unverified":3,"n_pointer_only":8}}},{"leaderboard":"/sota/long-tail-learning-on-mimic-cxr-lt","slug":"long-tail-learning-on-mimic-cxr-lt","dataset":"MIMIC-CXR-LT","dataset_url":"/dataset/mimic-cxr-lt","rows_in_archive":15,"metrics":["Balanced Accuracy"],"first_row_in_archive_order":{"model":"Decoupling (cRT)","paper_title":"Long-Tailed Classification of Thorax Diseases on Chest X-Ray: A New Benchmark Study","paper_url":"/paper/long-tailed-classification-of-thorax-diseases","paper_date":"2022-08-29","arxiv_id":"2208.13365","code_links":[{"title":"vita-group/longtailcxr","url":"https://github.com/vita-group/longtailcxr"}],"syntology":null}},{"leaderboard":"/sota/long-tail-learning-on-nih-cxr-lt","slug":"long-tail-learning-on-nih-cxr-lt","dataset":"NIH-CXR-LT","dataset_url":"/dataset/nih-cxr-lt","rows_in_archive":15,"metrics":["Balanced Accuracy"],"first_row_in_archive_order":{"model":"Decoupling (cRT)","paper_title":"Long-Tailed Classification of Thorax Diseases on Chest X-Ray: A New Benchmark Study","paper_url":"/paper/long-tailed-classification-of-thorax-diseases","paper_date":"2022-08-29","arxiv_id":"2208.13365","code_links":[{"title":"vita-group/longtailcxr","url":"https://github.com/vita-group/longtailcxr"}],"syntology":null}},{"leaderboard":"/sota/long-tail-learning-on-coco-mlt","slug":"long-tail-learning-on-coco-mlt","dataset":"COCO-MLT","dataset_url":"/dataset/coco-mlt","rows_in_archive":13,"metrics":["Average mAP"],"first_row_in_archive_order":{"model":"LMPT(ViT-B/16)","paper_title":"LMPT: Prompt Tuning with Class-Specific Embedding Loss for Long-tailed Multi-Label Visual Recognition","paper_url":"/paper/lmpt-prompt-tuning-with-class-specific","paper_date":"2023-05-08","arxiv_id":"2305.04536","code_links":[{"title":"richard-peng-xia/LMPT","url":"https://github.com/richard-peng-xia/LMPT"}],"syntology":{"n":9,"n_ran":0,"n_unverified":9,"n_pointer_only":0}}},{"leaderboard":"/sota/long-tail-learning-on-voc-mlt","slug":"long-tail-learning-on-voc-mlt","dataset":"VOC-MLT","dataset_url":"/dataset/voc-mlt","rows_in_archive":13,"metrics":["Average mAP"],"first_row_in_archive_order":{"model":"LMPT(ViT-B/16)","paper_title":"LMPT: Prompt Tuning with Class-Specific Embedding Loss for Long-tailed Multi-Label Visual Recognition","paper_url":"/paper/lmpt-prompt-tuning-with-class-specific","paper_date":"2023-05-08","arxiv_id":"2305.04536","code_links":[{"title":"richard-peng-xia/LMPT","url":"https://github.com/richard-peng-xia/LMPT"}],"syntology":{"n":9,"n_ran":0,"n_unverified":9,"n_pointer_only":0}}},{"leaderboard":"/sota/long-tail-learning-on-cifar-10-lt-r-50","slug":"long-tail-learning-on-cifar-10-lt-r-50","dataset":"CIFAR-10-LT (ρ=50)","dataset_url":null,"rows_in_archive":8,"metrics":["Error Rate"],"first_row_in_archive_order":{"model":"GLMC + SAM","paper_title":"Escaping Saddle Points for Effective Generalization on Class-Imbalanced Data","paper_url":"/paper/escaping-saddle-points-for-effective","paper_date":"2022-12-28","arxiv_id":"2212.13827","code_links":[{"title":"val-iisc/saddle-longtail","url":"https://github.com/val-iisc/saddle-longtail"}],"syntology":null}},{"leaderboard":"/sota/long-tail-learning-on-imagenet-glt","slug":"long-tail-learning-on-imagenet-glt","dataset":"ImageNet-GLT","dataset_url":null,"rows_in_archive":6,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"RIDE + IFL","paper_title":"Invariant Feature Learning for Generalized Long-Tailed Classification","paper_url":"/paper/invariant-feature-learning-for-generalized","paper_date":"2022-07-19","arxiv_id":"2207.09504","code_links":[{"title":"kaihuatang/generalized-long-tailed-benchmarks.pytorch","url":"https://github.com/kaihuatang/generalized-long-tailed-benchmarks.pytorch"}],"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}}},{"leaderboard":"/sota/long-tail-learning-on-egtea","slug":"long-tail-learning-on-egtea","dataset":"EGTEA","dataset_url":"/dataset/egtea","rows_in_archive":3,"metrics":["Average Precision","Average Recall"],"first_row_in_archive_order":{"model":"CDB-loss (3D- ResNeXt101)","paper_title":"Class-Wise Difficulty-Balanced Loss for Solving Class-Imbalance","paper_url":"/paper/class-wise-difficulty-balanced-loss-for","paper_date":"2020-10-05","arxiv_id":"2010.01824","code_links":[{"title":"hitachi-rd-cv/CDB-loss","url":"https://github.com/hitachi-rd-cv/CDB-loss"}],"syntology":{"n":2,"n_ran":0,"n_unverified":2,"n_pointer_only":2}}},{"leaderboard":"/sota/long-tail-learning-on-cifar-10-lt-r-200","slug":"long-tail-learning-on-cifar-10-lt-r-200","dataset":"CIFAR-10-LT (ρ=200)","dataset_url":null,"rows_in_archive":2,"metrics":["Error Rate"],"first_row_in_archive_order":{"model":"LDAM + DRW + SAM","paper_title":"Escaping Saddle Points for Effective Generalization on Class-Imbalanced Data","paper_url":"/paper/escaping-saddle-points-for-effective","paper_date":"2022-12-28","arxiv_id":"2212.13827","code_links":[{"title":"val-iisc/saddle-longtail","url":"https://github.com/val-iisc/saddle-longtail"}],"syntology":null}},{"leaderboard":"/sota/long-tail-learning-on-cifar-100-lt-r-200","slug":"long-tail-learning-on-cifar-100-lt-r-200","dataset":"CIFAR-100-LT (ρ=200)","dataset_url":null,"rows_in_archive":2,"metrics":["Error Rate"],"first_row_in_archive_order":{"model":"PaCo + SAM","paper_title":"Escaping Saddle Points for Effective Generalization on Class-Imbalanced Data","paper_url":"/paper/escaping-saddle-points-for-effective","paper_date":"2022-12-28","arxiv_id":"2212.13827","code_links":[{"title":"val-iisc/saddle-longtail","url":"https://github.com/val-iisc/saddle-longtail"}],"syntology":null}},{"leaderboard":"/sota/long-tail-learning-on-celeba-5","slug":"long-tail-learning-on-celeba-5","dataset":"CelebA-5","dataset_url":"/dataset/celeba","rows_in_archive":1,"metrics":["Error Rate"],"first_row_in_archive_order":{"model":"OPeN (WideResNet-28-10)","paper_title":"Pure Noise to the Rescue of Insufficient Data: Improving Imbalanced Classification by Training on Random Noise Images","paper_url":"/paper/pure-noise-to-the-rescue-of-insufficient-data","paper_date":"2021-12-16","arxiv_id":"2112.08810","code_links":[{"title":"shiranzada/pure-noise","url":"https://github.com/shiranzada/pure-noise"}],"syntology":null}},{"leaderboard":"/sota/long-tail-learning-on-lot-insts","slug":"long-tail-learning-on-lot-insts","dataset":"Lot-insts","dataset_url":"/dataset/lot-insts","rows_in_archive":1,"metrics":[" Macro-F1"],"first_row_in_archive_order":{"model":"Character-BERT+RS","paper_title":"Text Classification in the Wild: a Large-scale Long-tailed Name Normalization Dataset","paper_url":"/paper/text-classification-in-the-wild-a-large-scale","paper_date":"2023-02-19","arxiv_id":"2302.09509","code_links":[{"title":"lumia-group/lot-insts","url":"https://github.com/lumia-group/lot-insts"}],"syntology":null}},{"leaderboard":"/sota/long-tail-learning-on-mini-imagenet-lt","slug":"long-tail-learning-on-mini-imagenet-lt","dataset":"mini-ImageNet-LT","dataset_url":"/dataset/mini-imagenet-lt","rows_in_archive":1,"metrics":["Error Rate"],"first_row_in_archive_order":{"model":"TailCalibX","paper_title":"Feature Generation for Long-tail Classification","paper_url":"/paper/feature-generation-for-long-tail","paper_date":"2021-11-10","arxiv_id":"2111.05956","code_links":[{"title":"rahulvigneswaran/tailcalibx","url":"https://github.com/rahulvigneswaran/tailcalibx"}],"syntology":{"n":6,"n_ran":1,"n_unverified":5,"n_pointer_only":0}}}],"datasets":[{"url":"/dataset/cifar-10","name":"CIFAR-10","full_name":"CIFAR-10","num_papers_in_archive":16145},{"url":"/dataset/cifar-100","name":"CIFAR-100","full_name":"","num_papers_in_archive":9045},{"url":"/dataset/celeba","name":"CelebA","full_name":"CelebFaces Attributes Dataset","num_papers_in_archive":3477},{"url":"/dataset/kinetics","name":"Kinetics","full_name":"Kinetics Human Action Video Dataset","num_papers_in_archive":1341},{"url":"/dataset/inaturalist","name":"iNaturalist","full_name":"","num_papers_in_archive":603},{"url":"/dataset/imagenet-lt","name":"ImageNet-LT","full_name":"ImageNet Long-Tailed","num_papers_in_archive":219},{"url":"/dataset/egtea","name":"EGTEA","full_name":"EGTEA Gaze+","num_papers_in_archive":100},{"url":"/dataset/places-lt","name":"Places-LT","full_name":"","num_papers_in_archive":80},{"url":"/dataset/animal-kingdom","name":"Animal Kingdom","full_name":"","num_papers_in_archive":26},{"url":"/dataset/coco-mlt","name":"COCO-MLT","full_name":"","num_papers_in_archive":12},{"url":"/dataset/voc-mlt","name":"VOC-MLT","full_name":"","num_papers_in_archive":12},{"url":"/dataset/nih-cxr-lt","name":"NIH-CXR-LT","full_name":"Long-tailed (LT) NIH ChestXRay14","num_papers_in_archive":5},{"url":"/dataset/mimic-cxr-lt","name":"MIMIC-CXR-LT","full_name":"long-tailed version of MIMIC-CXR","num_papers_in_archive":4},{"url":"/dataset/mini-imagenet-lt","name":"mini-ImageNet-LT","full_name":"","num_papers_in_archive":2},{"url":"/dataset/imbalanced-minikinetics200","name":"Imbalanced-MiniKinetics200","full_name":"Imbalanced-MiniKinetics200","num_papers_in_archive":1},{"url":"/dataset/lot-insts","name":"Lot-insts","full_name":"Long-Tailed instituition names","num_papers_in_archive":1}],"subtasks":[{"url":"/task/long-tail-learning-with-class-descriptors","name":"Long-tail learning with class descriptors"}],"parent_tasks":[{"url":"/task/generalized-few-shot-classification","name":"Generalized Few-Shot Classification"},{"url":"/task/generalized-few-shot-learning","name":"Generalized Few-Shot Learning"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":93,"tagged_in_all":131,"items":[{"url":"/paper/focal-loss-for-dense-object-detection","title":"Focal Loss for Dense Object Detection","date":"2017-08-07","arxiv_id":"1708.02002","repositories_listed":234,"syntology":{"n":11,"n_ran":11,"n_unverified":0,"n_pointer_only":6}},{"url":"/paper/learning-transferable-visual-models-from","title":"Learning Transferable Visual Models From Natural Language Supervision","date":"2021-02-26","arxiv_id":"2103.00020","repositories_listed":82,"syntology":{"n":20,"n_ran":16,"n_unverified":4,"n_pointer_only":16}},{"url":"/paper/class-balanced-loss-based-on-effective-number","title":"Class-Balanced Loss Based on Effective Number of Samples","date":"2019-01-16","arxiv_id":"1901.05555","repositories_listed":11,"syntology":{"n":27,"n_ran":7,"n_unverified":20,"n_pointer_only":0}},{"url":"/paper/learning-imbalanced-datasets-with-label","title":"Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss","date":"2019-06-18","arxiv_id":"1906.07413","repositories_listed":7,"syntology":{"n":11,"n_ran":2,"n_unverified":9,"n_pointer_only":3}},{"url":"/paper/visual-prompt-tuning","title":"Visual Prompt Tuning","date":"2022-03-23","arxiv_id":"2203.12119","repositories_listed":6,"syntology":{"n":27,"n_ran":17,"n_unverified":10,"n_pointer_only":15}},{"url":"/paper/parametric-contrastive-learning","title":"Parametric Contrastive Learning","date":"2021-07-26","arxiv_id":"2107.12028","repositories_listed":5,"syntology":{"n":3,"n_ran":1,"n_unverified":2,"n_pointer_only":1}},{"url":"/paper/improving-calibration-for-long-tailed-1","title":"Improving Calibration for Long-Tailed Recognition","date":"2021-04-01","arxiv_id":"2104.00466","repositories_listed":5,"syntology":{"n":9,"n_ran":4,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/reslt-residual-learning-for-long-tailed","title":"ResLT: Residual Learning for Long-tailed Recognition","date":"2021-01-26","arxiv_id":"2101.10633","repositories_listed":5,"syntology":{"n":9,"n_ran":5,"n_unverified":4,"n_pointer_only":1}},{"url":"/paper/generalized-parametric-contrastive-learning","title":"Generalized Parametric Contrastive Learning","date":"2022-09-26","arxiv_id":"2209.12400","repositories_listed":4,"syntology":null},{"url":"/paper/decoupling-representation-and-classifier-for","title":"Decoupling Representation and Classifier for Long-Tailed Recognition","date":"2019-10-21","arxiv_id":"1910.09217","repositories_listed":4,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}},{"url":"/paper/improving-visual-prompt-tuning-by-gaussian","title":"Improving Visual Prompt Tuning by Gaussian Neighborhood Minimization for Long-Tailed Visual Recognition","date":"2024-10-28","arxiv_id":"2410.21042","repositories_listed":3,"syntology":{"n":8,"n_ran":1,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/class-balanced-distillation-for-long-tailed","title":"Class-Balanced Distillation for Long-Tailed Visual Recognition","date":"2021-04-12","arxiv_id":"2104.05279","repositories_listed":3,"syntology":null},{"url":"/paper/long-tail-learning-via-logit-adjustment","title":"Long-tail learning via logit adjustment","date":"2020-07-14","arxiv_id":"2007.07314","repositories_listed":3,"syntology":{"n":7,"n_ran":2,"n_unverified":5,"n_pointer_only":1}},{"url":"/paper/enhanced-long-tailed-recognition-with","title":"Enhanced Long-Tailed Recognition with Contrastive CutMix Augmentation","date":"2024-07-06","arxiv_id":"2407.04911","repositories_listed":2,"syntology":null},{"url":"/paper/deit-lt-distillation-strikes-back-for-vision","title":"DeiT-LT Distillation Strikes Back for Vision Transformer Training on Long-Tailed Datasets","date":"2024-04-03","arxiv_id":"2404.02900","repositories_listed":2,"syntology":null},{"url":"/paper/on-the-effectiveness-of-out-of-distribution","title":"On the Effectiveness of Out-of-Distribution Data in Self-Supervised Long-Tail Learning","date":"2023-06-08","arxiv_id":"2306.04934","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/global-and-local-mixture-consistency-1","title":"Global and Local Mixture Consistency Cumulative Learning for Long-tailed Visual Recognitions","date":"2023-05-15","arxiv_id":"2305.08661","repositories_listed":2,"syntology":{"n":10,"n_ran":7,"n_unverified":3,"n_pointer_only":5}},{"url":"/paper/curvature-balanced-feature-manifold-learning","title":"Predicting and Enhancing the Fairness of DNNs with the Curvature of Perceptual Manifolds","date":"2023-03-22","arxiv_id":"2303.12307","repositories_listed":2,"syntology":null},{"url":"/paper/balanced-product-of-experts-for-long-tailed","title":"Balanced Product of Calibrated Experts for Long-Tailed Recognition","date":"2022-06-10","arxiv_id":"2206.05260","repositories_listed":2,"syntology":null},{"url":"/paper/long-tailed-recognition-via-weight-balancing","title":"Long-Tailed Recognition via Weight Balancing","date":"2022-03-27","arxiv_id":"2203.14197","repositories_listed":2,"syntology":{"n":14,"n_ran":5,"n_unverified":9,"n_pointer_only":13}},{"url":"/paper/rebalanced-siamese-contrastive-mining-for","title":"Rebalanced Siamese Contrastive Mining for Long-Tailed Recognition","date":"2022-03-22","arxiv_id":"2203.11506","repositories_listed":2,"syntology":null},{"url":"/paper/a-simple-episodic-linear-probe-improves","title":"A Simple Episodic Linear Probe Improves Visual Recognition in the Wild","date":"2022-01-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/trustworthy-long-tailed-classification","title":"Trustworthy Long-Tailed Classification","date":"2021-11-17","arxiv_id":"2111.09030","repositories_listed":2,"syntology":null},{"url":"/paper/test-agnostic-long-tailed-recognition-by-test","title":"Self-Supervised Aggregation of Diverse Experts for Test-Agnostic Long-Tailed Recognition","date":"2021-07-20","arxiv_id":"2107.09249","repositories_listed":2,"syntology":{"n":6,"n_ran":4,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/disentangling-label-distribution-for-long","title":"Disentangling Label Distribution for Long-tailed Visual Recognition","date":"2020-12-01","arxiv_id":"2012.00321","repositories_listed":2,"syntology":null},{"url":"/paper/long-tailed-recognition-by-routing-diverse-1","title":"Long-tailed Recognition by Routing Diverse Distribution-Aware Experts","date":"2020-10-05","arxiv_id":"2010.01809","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/long-tailed-classification-by-keeping-the-1","title":"Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effect","date":"2020-09-28","arxiv_id":"2009.12991","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}},{"url":"/paper/m2m-imbalanced-classification-via-major-to","title":"M2m: Imbalanced Classification via Major-to-minor Translation","date":"2020-04-01","arxiv_id":"2004.00431","repositories_listed":2,"syntology":null},{"url":"/paper/large-scale-long-tailed-recognition-in-an","title":"Large-Scale Long-Tailed Recognition in an Open World","date":"2019-04-10","arxiv_id":"1904.05160","repositories_listed":2,"syntology":null},{"url":"/paper/multi-label-image-recognition-with-graph","title":"Multi-Label Image Recognition with Graph Convolutional Networks","date":"2019-04-07","arxiv_id":"1904.03582","repositories_listed":2,"syntology":null}],"syntology_records":17,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}