mlsanityData to 14 Oct 2026

SuperDisco: Super-Class Discovery Improves Visual Recognition for the Long-Tail

arXiv 2304.00101 ↗First posted 31 Mar 2023cs.CVcited by 9

Not on the map. Why?

Abstract (arXiv)

Modern image classifiers perform well on populated classes, while degrading considerably on tail classes with only a few instances. Humans, by contrast, effortlessly handle the long-tailed recognition challenge, since they can learn the tail representation based on different levels of semantic abstraction, making the learned tail features more discriminative. This phenomenon motivated us to propose SuperDisco, an algorithm that discovers super-class representations for long-tailed recognition using a graph model. We learn to construct the super-class graph to guide the representation learning to deal with long-tailed distributions. Through message passing on the super-class graph, image representations are rectified and refined by attending to the most relevant entities based on the semantic similarity among their super-classes. Moreover, we propose to meta-learn the super-class graph under the supervision of a prototype graph constructed from a small amount of imbalanced data. By doing so, we obtain a more robust super-class graph that further improves the long-tailed recognition performance. The consistent state-of-the-art experiments on the long-tailed CIFAR-100, ImageNet, Places and iNaturalist demonstrate the benefit of the discovered super-class graph for dealing with long-tailed distributions.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Builds on 62 of its 93 references that are in the map. First posted on arXiv 31 Mar 2023.

Builds on

62 of 93 references.

References · 62

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  3. 2017Graph Attention Networkscited by 8,923
  4. 2017Inductive Representation Learning on Large Graphscited by 6,320
  5. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  6. 2017Neural Message Passing for Quantum Chemistrycited by 3,487
  7. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  8. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,089
  9. 2019Class-Balanced Loss Based on Effective Number of Samplescited by 1,245
  10. 2013Spectral Networks and Locally Connected Networks on Graphscited by 1,102
  11. 2020Concept Bottleneck Modelscited by 1,032
  12. 2019Decoupling Representation and Classifier for Long-Tailed Recognitioncited by 809
38 more
  1. 2019Large-Scale Long-Tailed Recognition in an Open Worldcited by 705
  2. 2018Learning to Reweight Examples for Robust Deep Learningcited by 675
  3. 2020Long-tail learning via logit adjustmentcited by 618
  4. 2021Deep Long-Tailed Learning: A Surveycited by 417
  5. 2019BBN: Bilateral-Branch Network with Cumulative Learning for Long-Tailed Visual Recognitioncited by 403
  6. 2019Deep Learning for Image Super-resolution: A Surveycited by 369
  7. 2020Long-tailed Recognition by Routing Diverse Distribution-Aware Expertscited by 271
  8. 2020Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effectcited by 256
  9. 2015Deep Convolutional Networks on Graph-Structured Datacited by 246
  10. 2020Concept Whitening for Interpretable Image Recognitioncited by 225
  11. 2021Parametric Contrastive Learningcited by 217
  12. 2020Rethinking the Value of Labels for Improving Class-Imbalanced Learningcited by 216
  13. 2021Improving Calibration for Long-Tailed Recognitioncited by 212
  14. 2021Distribution Alignment: A Unified Framework for Long-tail Visual Recognitioncited by 198
  15. 2020Learning From Multiple Experts: Self-paced Knowledge Distillation for Long-tailed Classificationcited by 175
  16. 2021CReST: A Class-Rebalancing Self-Training Framework for Imbalanced Semi-Supervised Learningcited by 175
  17. 2018Large Scale Fine-Grained Categorization and Domain-Specific Transfer Learningcited by 174
  18. 2020Disentangling Label Distribution for Long-tailed Visual Recognitioncited by 172
  19. 2022Balanced Contrastive Learning for Long-Tailed Visual Recognitioncited by 144
  20. 2020Feature Space Augmentation for Long-Tailed Datacited by 136
  21. 2020M2m: Imbalanced Classification via Major-to-minor Translationcited by 134
  22. 2020Deep Representation Learning on Long-tailed Data: A Learnable Embedding Augmentation Perspectivecited by 120
  23. 2016Range Loss for Deep Face Recognition with Long-tailcited by 111
  24. 2020The Devil is in Classification: A Simple Framework for Long-tail Object Detection and Instance Segmentationcited by 108
  25. 2022Long-Tailed Recognition via Weight Balancingcited by 107
  26. 2021The Majority Can Help The Minority: Context-rich Minority Oversampling for Long-tailed Classificationcited by 100
  27. 2021MetaSAug: Meta Semantic Augmentation for Long-Tailed Visual Recognitioncited by 99
  28. 2021Influence-Balanced Loss for Imbalanced Visual Classificationcited by 91
  29. 2017The Devil is in the Tails: Fine-grained Classification in the Wildcited by 89
  30. 2021Distributional Robustness Loss for Long-tail Learningcited by 84
  31. 2021Re-distributing Biased Pseudo Labels for Semi-supervised Semantic Segmentation: A Baseline Investigationcited by 78
  32. 2021Self Supervision to Distillation for Long-Tailed Visual Recognitioncited by 73
  33. 2021Distilling Virtual Examples for Long-tailed Recognitioncited by 72
  34. 2017Class Rectification Hard Mining for Imbalanced Deep Learningcited by 67
  35. 2021RSG: A Simple but Effective Module for Learning Imbalanced Datasetscited by 61
  36. 2020Learning to Segment the Tailcited by 54
  37. 2016Factors in Finetuning Deep Model for object detectioncited by 53
  38. 2020Posterior Re-calibration for Imbalanced Datasetscited by 53

50 most cited of 62 All 62 (JSON)

Built on by

Cited by year

Citing papers per year: 2023: 3; 2024: 3; 2025: 3.

9 papers.

  1. 2023Learn to Categorize or Categorize to Learn? Self-Coding for Generalized Category Discoverycited by 39
  2. 2023iKUN: Speak to Trackers without Retrainingcited by 32
  3. 2024A Systematic Review on Long-Tailed Learningcited by 28
  4. 2023Toward Robustness in Multi-label Classification: A Data Augmentation Strategy against Imbalance and Noisecited by 11
  5. 2024O1O: Grouping of Known Classes to Identify Unknown Objects as Odd-One-Outcited by 1
  6. 2025Rethinking Contrastive Learning in Graph Anomaly Detection: A Clean-View Perspectivecited by 1
  7. 2024Training Over a Distribution of Hyperparameters for Enhanced Performance and Adaptability on Imbalanced Classificationcited by 0
  8. 2025Normalizing Batch Normalization for Long-Tailed Recognitioncited by 0
  9. 2025Rethinking Crystal Symmetry Prediction: A Decoupled Perspectivecited by 0