mlsanityData to 14 Oct 2026

Deep Representation Learning on Long-tailed Data: A Learnable Embedding Augmentation Perspective

arXiv 2002.10826 ↗First posted 25 Feb 2020cs.CVcited by 120

Not on the map. Why?

Abstract (arXiv)

This paper considers learning deep features from long-tailed data. We observe that in the deep feature space, the head classes and the tail classes present different distribution patterns. The head classes have a relatively large spatial span, while the tail classes have significantly small spatial span, due to the lack of intra-class diversity. This uneven distribution between head and tail classes distorts the overall feature space, which compromises the discriminative ability of the learned features. Intuitively, we seek to expand the distribution of the tail classes by transferring from the head classes, so as to alleviate the distortion of the feature space. To this end, we propose to construct each feature into a "feature cloud". If a sample belongs to a tail class, the corresponding feature cloud will have relatively large distribution range, in compensation to its lack of diversity. It allows each tail sample to push the samples from other classes far away, recovering the intra-class diversity of tail classes. Extensive experimental evaluations on person re-identification and face recognition tasks confirm the effectiveness of our method.

Key facts. Cited by 120 papers in the map (data through 14 Oct 2026). First posted on arXiv 25 Feb 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 32; 2022: 33; 2023: 27; 2024: 15; 2025: 6; 2026: 7.

120 papers.

Sort:

By area:

  1. 2021Deep Long-Tailed Learning: A Surveycited by 417
  2. 2021DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentationcited by 300
  3. 2021CReST: A Class-Rebalancing Self-Training Framework for Imbalanced Semi-Supervised Learningcited by 175
  4. 2023Towards Open Vocabulary Learning: A Surveycited by 166
  5. 2021Free Lunch for Few-shot Learning: Distribution Calibrationcited by 165
  6. 2022Registration based Few-Shot Anomaly Detectioncited by 133
  7. 2021Contrastive Learning based Hybrid Networks for Long-Tailed Image Classificationcited by 130
  8. 2021Self-supervised Learning is More Robust to Dataset Imbalancecited by 123
  9. 2022Retrieval Augmented Classification for Long-Tail Visual Recognitioncited by 106
  10. 2021MetaSAug: Meta Semantic Augmentation for Long-Tailed Visual Recognitioncited by 99
  11. 2021Distributional Robustness Loss for Long-tail Learningcited by 84
  12. 2021FASA: Feature Augmentation and Sampling Adaptation for Long-Tailed Instance Segmentationcited by 76
38 more
  1. 2022A Survey on Long-Tailed Visual Recognitioncited by 75
  2. 2021Lifelong Person Re-Identification via Adaptive Knowledge Accumulationcited by 57
  3. 2021Trustworthy Long-Tailed Classificationcited by 51
  4. 2021Adversarial Robustness under Long-Tailed Distributioncited by 50
  5. 2021A Simple Long-Tailed Recognition Baseline via Vision-Language Modelcited by 49
  6. 2023Class-Balancing Diffusion Modelscited by 48
  7. 2023MosaicFusion: Diffusion Models as Data Augmenters for Large Vocabulary Instance Segmentationcited by 35
  8. 2022Invariant Feature Learning for Generalized Long-Tailed Classificationcited by 34
  9. 2021GistNet: a Geometric Structure Transfer Network for Long-Tailed Recognitioncited by 31
  10. 2024MemeCLIP: Leveraging CLIP Representations for Multimodal Meme Classificationcited by 30
  11. 2024A Systematic Review on Long-Tailed Learningcited by 28
  12. 2021Class-Balanced Distillation for Long-Tailed Visual Recognitioncited by 27
  13. 2021Imagine by Reasoning: A Reasoning-Based Implicit Semantic Data Augmentation for Long-Tailed Classificationcited by 24
  14. 2021Balanced Knowledge Distillation for Long-tailed Learningcited by 23
  15. 2022Delving into Semantic Scale Imbalancecited by 22
  16. 2023Use Your Head: Improving Long-Tail Video Recognitioncited by 22
  17. 2023Feature Fusion from Head to Tail for Long-Tailed Visual Recognitioncited by 20
  18. 2021A Tale Of Two Long Tailscited by 19
  19. 2021Cross-Domain Empirical Risk Minimization for Unbiased Long-tailed Classificationcited by 19
  20. 2022Identifying Hard Noise in Long-Tailed Sample Distributioncited by 19
  21. 2022Imbalanced Semi-supervised Learning with Bias Adaptive Classifiercited by 18
  22. 2024Delving into the Trajectory Long-tail Distribution for Muti-object Trackingcited by 18
  23. 2023Fed-GraB: Federated Long-tailed Learning with Self-Adjusting Gradient Balancercited by 17
  24. 2021Graph Classification by Mixture of Diverse Expertscited by 16
  25. 2021Rethinking Re-Sampling in Imbalanced Semi-Supervised Learningcited by 16
  26. 2021Pure Noise to the Rescue of Insufficient Data: Improving Imbalanced Classification by Training on Random Noise Imagescited by 16
  27. 2022Towards better understanding and better generalization of few-shot classification in histology images with contrastive learningcited by 16
  28. 2023Distributionally Robust Post-hoc Classifiers under Prior Shiftscited by 16
  29. 2022Hierarchical Memory Learning for Fine-Grained Scene Graph Generationcited by 15
  30. 2022Spatial-Temporal Federated Learning for Lifelong Person Re-identification on Distributed Edgescited by 12
  31. 2023Transfer Knowledge from Head to Tail: Uncertainty Calibration under Long-tailed Distributioncited by 12
  32. 2024RepAugment: Input-Agnostic Representation-Level Augmentation for Respiratory Sound Classificationcited by 12
  33. 2021Predicate correlation learning for scene graph generationcited by 11
  34. 2022ELM: Embedding and Logit Margins for Long-Tail Learningcited by 10
  35. 2023Single-Stage Heavy-Tailed Food Classificationcited by 10
  36. 2024Geometric Prior Guided Feature Representation Learning for Long-Tailed Classificationcited by 10
  37. 2025A Comprehensive Survey on Imbalanced Data Learningcited by 10
  38. 2021Breadcrumbs: Adversarial Class-Balanced Sampling for Long-tailed Recognitioncited by 9

50 most cited of 120 All 120 (JSON)