mlsanityData to 7 Oct 2026

Class-incremental learning: survey and performance evaluation on image classification

arXiv 2010.15277 ↗First posted 28 Oct 2020cs.LG cs.CVcited by 446

Not on the map. Why?

Abstract (arXiv)

For future learning systems, incremental learning is desirable because it allows for: efficient resource usage by eliminating the need to retrain from scratch at the arrival of new data; reduced memory usage by preventing or limiting the amount of data required to be stored -- also important when privacy limitations are imposed; and learning that more closely resembles human learning. The main challenge for incremental learning is catastrophic forgetting, which refers to the precipitous drop in performance on previously learned tasks after learning a new one. Incremental learning of deep neural networks has seen explosive growth in recent years. Initial work focused on task-incremental learning, where a task-ID is provided at inference time. Recently, we have seen a shift towards class-incremental learning where the learner must discriminate at inference time between all classes seen in previous tasks without recourse to a task-ID. In this paper, we provide a complete survey of existing class-incremental learning methods for image classification, and in particular, we perform an extensive experimental evaluation on thirteen class-incremental methods. We consider several new experimental scenarios, including a comparison of class-incremental methods on multiple large-scale image classification datasets, an investigation into small and large domain shifts, and a comparison of various network architectures.

Key facts. Cited by 446 papers in the map (data through 7 Oct 2026). First posted on arXiv 28 Oct 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 32; 2022: 62; 2023: 104; 2024: 108; 2025: 90; 2026: 50.

446 papers.

Sort:

By area:

  1. 2022DualPrompt: Complementary Prompting for Rehearsal-free Continual Learningcited by 635
  2. 2024Hybrid LLM: Cost-Efficient and Quality-Aware Query Routingcited by 354
  3. 2022FOSTER: Feature Boosting and Compression for Class-Incremental Learningcited by 228
  4. 2023Class-Incremental Learning: A Surveycited by 209
  5. 2023Revisiting Class-Incremental Learning with Pre-Trained Models: Generalizability and Adaptivity are All You Needcited by 183
  6. 2022A Model or 603 Exemplars: Towards Memory-Efficient Class-Incremental Learningcited by 152
  7. 2024Continual Learning with Pre-Trained Models: A Surveycited by 151
  8. 2021Supervised Contrastive Replay: Revisiting the Nearest Class Mean Classifier in Online Class-Incremental Continual Learningcited by 140
  9. 2021Avalanche: an End-to-End Library for Continual Learningcited by 124
  10. 2022FeTrIL: Feature Translation for Exemplar-Free Class-Incremental Learningcited by 120
  11. 2021Preservation of the Global Knowledge by Not-True Distillation in Federated Learningcited by 87
  12. 2022Few-Shot Class-Incremental Learning by Sampling Multi-Phase Taskscited by 87
38 more
  1. 2023FeCAM: Exploiting the Heterogeneity of Class Distributions in Exemplar-Free Continual Learningcited by 86
  2. 2022Continual Learning of Natural Language Processing Tasks: A Surveycited by 83
  3. 2023Learning without Forgetting for Vision-Language Modelscited by 79
  4. 2024Continual Learning and Catastrophic Forgettingcited by 73
  5. 2024MagMax: Leveraging Model Merging for Seamless Continual Learningcited by 67
  6. 2023A Comprehensive Survey of Forgetting in Deep Learning Beyond Continual Learningcited by 66
  7. 2023PILOT: A Pre-Trained Model-Based Continual Learning Toolboxcited by 64
  8. 2023Computationally Budgeted Continual Learning: What Does Matter?cited by 61
  9. 2023Continual Learning: Applications and the Road Forwardcited by 59
  10. 2021Recent Advances of Continual Learning in Computer Vision: An Overviewcited by 55
  11. 2023Learning with Fantasy: Semantic-Aware Virtual Contrastive Constraint for Few-Shot Class-Incremental Learningcited by 55
  12. 2021Subspace Regularizers for Few-Shot Class Incremental Learningcited by 54
  13. 2022An Efficient Domain-Incremental Learning Approach to Drive in All Weather Conditionscited by 54
  14. 2024Model Tailor: Mitigating Catastrophic Forgetting in Multi-modal Large Language Modelscited by 54
  15. 2023No One Left Behind: Real-World Federated Class-Incremental Learningcited by 53
  16. 2023Online Prototype Learning for Online Continual Learningcited by 53
  17. 2024Consistent Prompting for Rehearsal-Free Continual Learningcited by 52
  18. 2021Mimicking the Oracle: An Initial Phase Decorrelation Approach for Class Incremental Learningcited by 49
  19. 2022Open-environment Machine Learningcited by 48
  20. 2024Class-Incremental Learning with CLIP: Adaptive Representation Adjustment and Parameter Fusioncited by 47
  21. 2024Recent Advances of Foundation Language Models-based Continual Learning: A Surveycited by 46
  22. 2021Posterior Meta-Replay for Continual Learningcited by 45
  23. 2024Mixture of Experts Meets Prompt-Based Continual Learningcited by 43
  24. 2021A distillation-based approach integrating continual learning and federated learning for pervasive servicescited by 42
  25. 2022Class-incremental Novel Class Discoverycited by 42
  26. 2023Achieving a Better Stability-Plasticity Trade-off via Auxiliary Networks in Continual Learningcited by 41
  27. 2023Weighted Ensemble Models Are Strong Continual Learnerscited by 41
  28. 2021Class-Incremental Learning with Generative Classifierscited by 39
  29. 2023EgoObjects: A Large-Scale Egocentric Dataset for Fine-Grained Object Understandingcited by 39
  30. 2024Recent Advances of Multimodal Continual Learning: A Comprehensive Surveycited by 39
  31. 2021Continually Learning Self-Supervised Representations with Projected Functional Regularizationcited by 38
  32. 2024Divide and not forget: Ensemble of selectively trained experts in Continual Learningcited by 38
  33. 2024Elastic Feature Consolidation for Cold Start Exemplar-Free Incremental Learningcited by 37
  34. 2024Gradient Reweighting: Towards Imbalanced Class-Incremental Learningcited by 37
  35. 2021Continual Learning for Blind Image Quality Assessmentcited by 36
  36. 2022Long-Tailed Class Incremental Learningcited by 36
  37. 2024Make Continual Learning Stronger via C-Flatcited by 35
  38. 2023Avalanche: A PyTorch Library for Deep Continual Learningcited by 33

50 most cited of 446 All 446 (JSON)