mlsanityData to 14 Oct 2026

Aligned Contrastive Loss for Long-Tailed Recognition

arXiv 2506.01071 ↗First posted 1 Jun 2025cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

In this paper, we propose an Aligned Contrastive Learning (ACL) algorithm to address the long-tailed recognition problem. Our findings indicate that while multi-view training boosts the performance, contrastive learning does not consistently enhance model generalization as the number of views increases. Through theoretical gradient analysis of supervised contrastive learning (SCL), we identify gradient conflicts, and imbalanced attraction and repulsion gradients between positive and negative pairs as the underlying issues. Our ACL algorithm is designed to eliminate these problems and demonstrates strong performance across multiple benchmarks. We validate the effectiveness of ACL through experiments on long-tailed CIFAR, ImageNet, Places, and iNaturalist datasets. Results show that ACL achieves new state-of-the-art performance.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 41 of its 52 references that are in the map. First posted on arXiv 1 Jun 2025.

Builds on

41 of 52 references.

References · 41

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  3. 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
  4. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  5. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,750
  6. 2020Exploring Simple Siamese Representation Learningcited by 2,866
  7. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,857
  8. 2020Supervised Contrastive Learningcited by 2,829
  9. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,546
  10. 2017Improved Regularization of Convolutional Neural Networks with Cutoutcited by 1,628
  11. 2021An Empirical Study of Training Self-Supervised Vision Transformerscited by 1,616
  12. 2020Big Self-Supervised Models are Strong Semi-Supervised Learnerscited by 1,380
29 more
  1. 2019Class-Balanced Loss Based on Effective Number of Samplescited by 1,245
  2. 2019Decoupling Representation and Classifier for Long-Tailed Recognitioncited by 809
  3. 2018AutoAugment: Learning Augmentation Policies from Datacited by 730
  4. 2019Large-Scale Long-Tailed Recognition in an Open Worldcited by 705
  5. 2020Long-tail learning via logit adjustmentcited by 618
  6. 2017A systematic study of the class imbalance problem in convolutional neural networkscited by 513
  7. 2021Deep Long-Tailed Learning: A Surveycited by 417
  8. 2019BBN: Bilateral-Branch Network with Cumulative Learning for Long-Tailed Visual Recognitioncited by 403
  9. 2020Balanced Meta-Softmax for Long-Tailed Visual Recognitioncited by 400
  10. 2020Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effectcited by 256
  11. 2018What is the Effect of Importance Weighting in Deep Learning?cited by 251
  12. 2021Parametric Contrastive Learningcited by 217
  13. 2021Improving Calibration for Long-Tailed Recognitioncited by 212
  14. 2021Distribution Alignment: A Unified Framework for Long-tail Visual Recognitioncited by 198
  15. 2020Disentangling Label Distribution for Long-tailed Visual Recognitioncited by 172
  16. 2015Cost Sensitive Learning of Deep Feature Representations from Imbalanced Datacited by 167
  17. 2022Balanced Contrastive Learning for Long-Tailed Visual Recognitioncited by 144
  18. 2021Targeted Supervised Contrastive Learning for Long-Tailed Recognitioncited by 132
  19. 2021Contrastive Learning based Hybrid Networks for Long-Tailed Image Classificationcited by 130
  20. 2022Inducing Neural Collapse in Imbalanced Learning: Do We Really Need a Learnable Classifier at the End of Deep Neural Network?cited by 100
  21. 2022Generalized Parametric Contrastive Learningcited by 45
  22. 2024Probabilistic Contrastive Learning for Long-Tailed Visual Recognitioncited by 42
  23. 2021Drawing Multiple Augmentation Samples Per Image During Training Efficiently Decreases Test Errorcited by 33
  24. 2023Generalized Logit Adjustment: Calibrating Fine-tuned Models by Removing Label Bias in Foundation Modelscited by 32
  25. 2023Inducing Neural Collapse in Deep Long-tailed Learningcited by 28
  26. 2023Subclass-balancing Contrastive Learning for Long-tailed Recognitioncited by 26
  27. 2023Long-Tailed Recognition by Mutual Information Maximization between Latent Features and Ground-Truth Labelscited by 16
  28. 2023Decoupled Training for Long-Tailed Classification With Stochastic Representationscited by 13
  29. 2024Decoupled Contrastive Learning for Long-Tailed Recognitioncited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026CLEAR: Class-wise Expert Aggregation with Structured Sampling for Long-Tailed Classificationcited by 0