mlsanityData to 14 Oct 2026

LTRL: Boosting Long-tail Recognition via Reflective Learning

arXiv 2407.12568 ↗First posted 17 Jul 2024cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

In real-world scenarios, where knowledge distributions exhibit long-tail. Humans manage to master knowledge uniformly across imbalanced distributions, a feat attributed to their diligent practices of reviewing, summarizing, and correcting errors. Motivated by this learning process, we propose a novel learning paradigm, called reflecting learning, in handling long-tail recognition. Our method integrates three processes for reviewing past predictions during training, summarizing and leveraging the feature relation across classes, and correcting gradient conflict for loss functions. These designs are lightweight enough to plug and play with existing long-tail learning methods, achieving state-of-the-art performance in popular long-tail visual benchmarks. The experimental results highlight the great potential of reflecting learning in dealing with long-tail recognition.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 44 of its 56 references that are in the map. First posted on arXiv 17 Jul 2024.

Builds on

44 of 56 references.

References · 44

  1. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  2. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,475
  3. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
  4. 2019RandAugment: Practical automated data augmentation with a reduced search spacecited by 2,269
  5. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,085
  6. 2019Class-Balanced Loss Based on Effective Number of Samplescited by 1,245
  7. 2016Temporal Ensembling for Semi-Supervised Learningcited by 1,057
  8. 2019Learning Imbalanced Datasets with Label-Distribution-Aware Margin Losscited by 989
  9. 2017Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learningcited by 920
  10. 2019Decoupling Representation and Classifier for Long-Tailed Recognitioncited by 809
  11. 2019Large-Scale Long-Tailed Recognition in an Open Worldcited by 705
  12. 2020Long-tail learning via logit adjustmentcited by 618
32 more
  1. 2017A systematic study of the class imbalance problem in convolutional neural networkscited by 513
  2. 2016Regularization With Stochastic Transformations and Perturbations for Deep Semi-Supervised Learningcited by 441
  3. 2021Deep Long-Tailed Learning: A Surveycited by 417
  4. 2019BBN: Bilateral-Branch Network with Cumulative Learning for Long-Tailed Visual Recognitioncited by 403
  5. 2020Balanced Meta-Softmax for Long-Tailed Visual Recognitioncited by 400
  6. 2020Long-tailed Recognition by Routing Diverse Distribution-Aware Expertscited by 271
  7. 2018What is the Effect of Importance Weighting in Deep Learning?cited by 251
  8. 2014Learning with Pseudo-Ensemblescited by 241
  9. 2021Parametric Contrastive Learningcited by 217
  10. 2020Rethinking the Value of Labels for Improving Class-Imbalanced Learningcited by 216
  11. 2021Improving Calibration for Long-Tailed Recognitioncited by 212
  12. 2020Learning From Multiple Experts: Self-paced Knowledge Distillation for Long-tailed Classificationcited by 175
  13. 2015Cost Sensitive Learning of Deep Feature Representations from Imbalanced Datacited by 167
  14. 2020Remix: Rebalanced Mixupcited by 144
  15. 2022Balanced Contrastive Learning for Long-Tailed Visual Recognitioncited by 144
  16. 2021Contrastive Learning based Hybrid Networks for Long-Tailed Image Classificationcited by 130
  17. 2020Deep Representation Learning on Long-tailed Data: A Learnable Embedding Augmentation Perspectivecited by 120
  18. 2022Long-Tailed Recognition via Weight Balancingcited by 107
  19. 2021Self-Supervised Aggregation of Diverse Experts for Test-Agnostic Long-Tailed Recognitioncited by 95
  20. 2021ACE: Ally Complementary Experts for Solving Long-Tailed Recognition in One-Shotcited by 86
  21. 2021Distilling Virtual Examples for Long-tailed Recognitioncited by 72
  22. 2022Nested Collaborative Learning for Long-Tailed Visual Recognitioncited by 63
  23. 2024LTGC: Long-tail Recognition via Leveraging LLMs-driven Generated Contentcited by 33
  24. 2017The iNaturalist Species Classification and Detection Datasetcited by 29
  25. 2022Constructing Balance from Imbalance for Long-tailed Image Recognitioncited by 25
  26. 2024Diff-Tracker: Text-to-Image Diffusion Models are Unsupervised Trackerscited by 24
  27. 2022Balanced Product of Calibrated Experts for Long-Tailed Recognitioncited by 20
  28. 2023MDCS: More Diverse Experts with Consistency Self-distillation for Long-tailed Recognitioncited by 19
  29. 2021Long-tail Recognition via Compositional Knowledge Transfercited by 16
  30. 2020Memory-based Jitter: Improving Visual Recognition on Long-tailed Data with Diversity In Memorycited by 15
  31. 2023Decoupled Training for Long-Tailed Classification With Stochastic Representationscited by 13
  32. 2018Left-Right Comparative Recurrent Model for Stereo Matchingcited by 12

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 4.

6 papers.

  1. 2025Divide, Weight, and Route: Difficulty-Aware Optimization with Dynamic Expert Fusion for Long-tailed Recognitioncited by 1
  2. 2025LT-Soups: Bridging Head and Tail Classes via Subsampled Model Soupscited by 1
  3. 2026Deep Convolutional Large-Margin ℓp-SVDD for Visual Anomaly Detectioncited by 0
  4. 2026CLEAR: Class-wise Expert Aggregation with Structured Sampling for Long-Tailed Classificationcited by 0
  5. 2026VICAL: Vicinal Consistency Alignment for Long-Tailed Visual Recognitioncited by 0
  6. 2026Rethinking Class Imbalance for Single-Cell Foundation Models: A Systematic Benchmark Across Architectures and Long-Tail Loss Functionscited by 0