Long-tail Learning

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

20 leaderboard tables shown for this task, 20 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted. 10 shown of 20 until expanded.

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

16 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

1 subtask in the archive's task tree.

Parent tasks archive 2025-07-28

Most implemented papers archive 2025-07-28

30 shown of 93 papers with code (131 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• Focal Loss for Dense Object Detection
  7 Aug 2017 234 repositories listed Syntology ran 11 of 11 samples · 0 unverified · 6 pointer-only (licence)
  Our novel Focal Loss focuses training on a sparse set of hard examples and prevents the vast number of easy negatives from overwhelming the detector during training.
• Learning Transferable Visual Models From Natural Language Supervision
  26 Feb 2021 82 repositories listed Syntology ran 16 of 20 samples · 4 unverified · 16 pointer-only (licence)
  State-of-the-art computer vision systems are trained to predict a fixed set of predetermined object categories.
• Class-Balanced Loss Based on Effective Number of Samples
  16 Jan 2019 11 repositories listed Syntology ran 7 of 27 samples · 20 unverified
  We design a re-weighting scheme that uses the effective number of samples for each class to re-balance the loss, thereby yielding a class-balanced loss.
• Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss
  18 Jun 2019 7 repositories listed Syntology ran 2 of 11 samples · 9 unverified · 3 pointer-only (licence)
  Deep learning algorithms can fare poorly when the training dataset suffers from heavy class-imbalance but the testing criterion requires good generalization on less frequent classes.
• Visual Prompt Tuning
  23 Mar 2022 6 repositories listed Syntology ran 17 of 27 samples · 10 unverified · 15 pointer-only (licence)
  The current modus operandi in adapting pre-trained models involves updating all the backbone parameters, ie, full fine-tuning.
• Parametric Contrastive Learning
  26 Jul 2021 5 repositories listed Syntology ran 1 of 3 samples · 2 unverified · 1 pointer-only (licence)
  In this paper, we propose Parametric Contrastive Learning (PaCo) to tackle long-tailed recognition.
• Improving Calibration for Long-Tailed Recognition
  1 Apr 2021 5 repositories listed Syntology ran 4 of 9 samples · 5 unverified
  Motivated by the fact that predicted probability distributions of classes are highly related to the numbers of class instances, we propose label-aware smoothing to deal with different degrees of over-confidence for…
• ResLT: Residual Learning for Long-tailed Recognition
  26 Jan 2021 5 repositories listed Syntology ran 5 of 9 samples · 4 unverified · 1 pointer-only (licence)
  From this perspective, the trivial solution utilizes different branches for the head, medium, and tail classes respectively, and then sums their outputs as the final results is not feasible.
• Generalized Parametric Contrastive Learning
  26 Sep 2022 4 repositories listed
  Based on theoretical analysis, we observe that supervised contrastive loss tends to bias high-frequency classes and thus increases the difficulty of imbalanced learning.
• Decoupling Representation and Classifier for Long-Tailed Recognition
  21 Oct 2019 4 repositories listed Syntology ran 2 of 2 samples · 0 unverified · 2 pointer-only (licence)
  The long-tail distribution of the visual world poses great challenges for deep learning based classification models on how to handle the class imbalance problem.
• Improving Visual Prompt Tuning by Gaussian Neighborhood Minimization for Long-Tailed Visual Recognition
  28 Oct 2024 3 repositories listed Syntology ran 1 of 8 samples · 7 unverified
  To address this issue, we propose a novel method called Random SAM prompt tuning (RSAM-PT) to improve the model generalization, requiring only one-step gradient computation at each step.
• Class-Balanced Distillation for Long-Tailed Visual Recognition
  12 Apr 2021 3 repositories listed
  An effective and simple approach to long-tailed visual recognition is to learn feature representations and a classifier separately, with instance and class-balanced sampling, respectively.
• Long-tail learning via logit adjustment
  14 Jul 2020 3 repositories listed Syntology ran 2 of 7 samples · 5 unverified · 1 pointer-only (licence)
  Real-world classification problems typically exhibit an imbalanced or long-tailed label distribution, wherein many labels are associated with only a few samples.
• Enhanced Long-Tailed Recognition with Contrastive CutMix Augmentation
  6 Jul 2024 2 repositories listed
  Real-world data often follows a long-tailed distribution, where a few head classes occupy most of the data and a large number of tail classes only contain very limited samples.
• DeiT-LT Distillation Strikes Back for Vision Transformer Training on Long-Tailed Datasets
  3 Apr 2024 2 repositories listed
  In DeiT-LT, we introduce an efficient and effective way of distillation from CNN via distillation DIST token by using out-of-distribution images and re-weighting the distillation loss to enhance focus on tail classes.
• On the Effectiveness of Out-of-Distribution Data in Self-Supervised Long-Tail Learning
  8 Jun 2023 2 repositories listed Syntology ran 1 of 1 samples · 0 unverified
  Recent work shows that the long-tailed learning performance could be boosted by sampling extra in-domain (ID) data for self-supervised training, however, large-scale ID data which can rebalance the minority classes are…
• Global and Local Mixture Consistency Cumulative Learning for Long-tailed Visual Recognitions
  15 May 2023 2 repositories listed Syntology ran 7 of 10 samples · 3 unverified · 5 pointer-only (licence)
  In this paper, our goal is to design a simple learning paradigm for long-tail visual recognition, which not only improves the robustness of the feature extractor but also alleviates the bias of the classifier towards…
• Predicting and Enhancing the Fairness of DNNs with the Curvature of Perceptual Manifolds
  22 Mar 2023 2 repositories listed
  To address the challenges of long-tailed classification, researchers have proposed several approaches to reduce model bias, most of which assume that classes with few samples are weak classes.
• Balanced Product of Calibrated Experts for Long-Tailed Recognition
  10 Jun 2022 2 repositories listed
  We show how to properly define these distributions and combine the experts in order to achieve unbiased predictions, by proving that the ensemble is Fisher-consistent for minimizing the balanced error.
• Long-Tailed Recognition via Weight Balancing
  27 Mar 2022 2 repositories listed Syntology ran 5 of 14 samples · 9 unverified · 13 pointer-only (licence)
  In contrast, weight decay penalizes larger weights more heavily and so learns small balanced weights; the MaxNorm constraint encourages growing small weights within a norm ball but caps all the weights by the radius.
• Rebalanced Siamese Contrastive Mining for Long-Tailed Recognition
  22 Mar 2022 2 repositories listed
  Given the promising performance of contrastive learning, we propose Rebalanced Siamese Contrastive Mining (ResCom) to tackle imbalanced recognition.
• A Simple Episodic Linear Probe Improves Visual Recognition in the Wild
  1 Jan 2022 2 repositories listed
  In this paper, we propose an episodic linear probing (ELP) classifier to reflect the generalization of visual representations in an online manner.
• Trustworthy Long-Tailed Classification
  17 Nov 2021 2 repositories listed
  To address these issues, we propose a Trustworthy Long-tailed Classification (TLC) method to jointly conduct classification and uncertainty estimation to identify hard samples in a multi-expert framework.
• Self-Supervised Aggregation of Diverse Experts for Test-Agnostic Long-Tailed Recognition
  20 Jul 2021 2 repositories listed Syntology ran 4 of 6 samples · 2 unverified
  Existing long-tailed recognition methods, aiming to train class-balanced models from long-tailed data, generally assume the models would be evaluated on the uniform test class distribution.
• Disentangling Label Distribution for Long-tailed Visual Recognition
  1 Dec 2020 2 repositories listed
  Although this method surpasses state-of-the-art methods on benchmark datasets, it can be further improved by directly disentangling the source label distribution from the model prediction in the training phase.
• Long-tailed Recognition by Routing Diverse Distribution-Aware Experts
  5 Oct 2020 2 repositories listed Syntology ran 1 of 1 samples · 0 unverified
  We take a dynamic view of the training data and provide a principled model bias and variance analysis as the training data fluctuates: Existing long-tail classifiers invariably increase the model variance and the…
• Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effect
  28 Sep 2020 2 repositories listed Syntology ran 2 of 2 samples · 0 unverified · 2 pointer-only (licence)
  On one hand, it has a harmful causal effect that misleads the tail prediction biased towards the head.
• M2m: Imbalanced Classification via Major-to-minor Translation
  1 Apr 2020 2 repositories listed
  In most real-world scenarios, labeled training datasets are highly class-imbalanced, where deep neural networks suffer from generalizing to a balanced testing criterion.
• Large-Scale Long-Tailed Recognition in an Open World
  10 Apr 2019 2 repositories listed
  We define Open Long-Tailed Recognition (OLTR) as learning from such naturally distributed data and optimizing the classification accuracy over a balanced test set which include head, tail, and open classes.
• Multi-Label Image Recognition with Graph Convolutional Networks
  7 Apr 2019 2 repositories listed
  The task of multi-label image recognition is to predict a set of object labels that present in an image.

Syntology lines on 17 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.