mlsanityData to 14 Oct 2026

Breadcrumbs: Adversarial Class-Balanced Sampling for Long-tailed Recognition

arXiv 2105.00127 ↗First posted 1 May 2021cs.CVcited by 9

Not on the map. Why?

Abstract (arXiv)

The problem of long-tailed recognition, where the number of examples per class is highly unbalanced, is considered. While training with class-balanced sampling has been shown effective for this problem, it is known to over-fit to few-shot classes. It is hypothesized that this is due to the repeated sampling of examples and can be addressed by feature space augmentation. A new feature augmentation strategy, EMANATE, based on back-tracking of features across epochs during training, is proposed. It is shown that, unlike class-balanced sampling, this is an adversarial augmentation strategy. A new sampling procedure, Breadcrumb, is then introduced to implement adversarial class-balanced sampling without extra computation. Experiments on three popular long-tailed recognition datasets show that Breadcrumb training produces classifiers that outperform existing solutions to the problem.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Builds on 30 of its 40 references that are in the map. First posted on arXiv 1 May 2021.

Builds on

30 of 40 references.

References · 30

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  3. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  4. 2014Deep Learning Face Attributes in the Wildcited by 3,693
  5. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  6. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,546
  7. 2016Matching Networks for One Shot Learningcited by 2,255
  8. 2019Class-Balanced Loss Based on Effective Number of Samplescited by 1,245
  9. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,143
  10. 2019Learning Imbalanced Datasets with Label-Distribution-Aware Margin Losscited by 989
  11. 2019Decoupling Representation and Classifier for Long-Tailed Recognitioncited by 809
  12. 2019Large-Scale Long-Tailed Recognition in an Open Worldcited by 705
18 more
  1. 2018Meta-Learning with Latent Embedding Optimizationcited by 476
  2. 2015Deep Metric Learning via Lifted Structured Feature Embeddingcited by 449
  3. 2019BBN: Bilateral-Branch Network with Cumulative Learning for Long-Tailed Visual Recognitioncited by 403
  4. 2018Dynamic Few-Shot Visual Learning without Forgettingcited by 385
  5. 2017Feature Generating Networks for Zero-Shot Learningcited by 257
  6. 2018Probabilistic Model-Agnostic Meta-Learningcited by 256
  7. 2020Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effectcited by 256
  8. 2018Low-Shot Learning from Imaginary Datacited by 181
  9. 2020Learning From Multiple Experts: Self-paced Knowledge Distillation for Long-tailed Classificationcited by 175
  10. 2020Disentangling Label Distribution for Long-tailed Visual Recognitioncited by 172
  11. 2019f-VAEGAN-D2: A Feature Generating Framework for Any-Shot Learningcited by 164
  12. 2020Deep Representation Learning on Long-tailed Data: A Learnable Embedding Augmentation Perspectivecited by 120
  13. 2016Range Loss for Deep Face Recognition with Long-tailcited by 111
  14. 2018Deep Imbalanced Learning for Face Recognition and Attribute Predictioncited by 91
  15. 2018Multi-modal Cycle-consistent Generalized Zero-Shot Learningcited by 87
  16. 2019Image Deformation Meta-Networks for One-Shot Learningcited by 56
  17. 2018Feature Space Transfer for Data Augmentationcited by 21
  18. 2020Long-Tailed Recognition Using Class-Balanced Expertscited by 10

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 3; 2023: 1; 2024: 2; 2025: 2; 2026: 1.

9 papers.

  1. 2022A Survey on Long-Tailed Visual Recognitioncited by 75
  2. 2022Learning Imbalanced Data with Vision Transformerscited by 34
  3. 2023Balancing Logit Variation for Long-tailed Semantic Segmentationcited by 26
  4. 2025Focal-SAM: Focal Sharpness-Aware Minimization for Long-Tailed Classificationcited by 14
  5. 2025A Square Peg in a Square Hole: Meta-Expert for Long-Tailed Semi-Supervised Learningcited by 7
  6. 2022DBN-Mix: Training Dual Branch Network Using Bilateral Mixup Augmentation for Long-Tailed Visual Recognitioncited by 6
  7. 2024IMWA: Iterative Model Weight Averaging Benefits Class-Imbalanced Learning Taskscited by 1
  8. 2024Partial Knowledge Distillation for Alleviating the Inherent Inter-Class Discrepancy in Federated Learningcited by 0
  9. 2026Manifold-Constrained Adversarial Training for Long-Tailed Robustness via Geometric Alignmentcited by 0