mlsanityData to 14 Oct 2026

iCaRL: Incremental Classifier and Representation Learning

arXiv 1611.07725 ↗First posted 23 Nov 2016cs.CV cs.LG stat.MLcited by 2,333

Not on the map. Why?

Cited by 82 in Knowledge distillation, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

A major open problem on the road to artificial intelligence is the development of incrementally learning systems that learn about more and more concepts over time from a stream of data. In this work, we introduce a new training strategy, iCaRL, that allows learning in such a class-incremental way: only the training data for a small number of classes has to be present at the same time and new classes can be added progressively. iCaRL learns strong classifiers and a data representation simultaneously. This distinguishes it from earlier works that were fundamentally limited to fixed data representations and therefore incompatible with deep learning architectures. We show by experiments on CIFAR-100 and ImageNet ILSVRC 2012 data that iCaRL can learn many classes incrementally over a long period of time where other strategies quickly fail.

Key facts. Cited by 2,333 papers in the map (data through 14 Oct 2026). First posted on arXiv 23 Nov 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 288; 2022: 363; 2023: 451; 2024: 467; 2025: 419; 2026: 345.

2,333 papers.

Sort:

By area:

  1. 2021Learning to Prompt for Continual Learningcited by 944
  2. 2023A Comprehensive Survey of Continual Learning: Theory, Method and Applicationcited by 872
  3. 2022DualPrompt: Complementary Prompting for Rehearsal-free Continual Learningcited by 642
  4. 2022Continual Test-Time Domain Adaptationcited by 525
  5. 2022CODA-Prompt: COntinual Decomposed Attention-based Prompting for Rehearsal-Free Continual Learningcited by 450
  6. 2021Dataset Condensation with Distribution Matchingcited by 365
  7. 2023A Comprehensive Survey on Test-Time Adaptation under Distribution Shiftscited by 359
  8. 2021DER: Dynamically Expandable Representation for Class Incremental Learningcited by 355
  9. 2021Gradient Projection Memory for Continual Learningcited by 348
  10. 2022Prompt-aligned Gradient for Prompt Tuningcited by 341
  11. 2021Towards Open World Object Detectioncited by 297
  12. 2021Dataset Condensation with Differentiable Siamese Augmentationcited by 291
38 more
  1. 2021DyTox: Transformers for Continual Learning with DYnamic TOken eXpansioncited by 291
  2. 2021DeepViT: Towards Deeper Vision Transformercited by 289
  3. 2021Rainbow Memory: Continual Learning with a Memory of Diverse Samplescited by 273
  4. 2022S-Prompts Learning with Pre-trained Transformers: An Occam's Razor for Domain Incremental Learningcited by 246
  5. 2021Online Continual Learning in Image Classification: An Empirical Surveycited by 245
  6. 2021Co2L: Contrastive Continual Learningcited by 244
  7. 2024Continual Learning of Large Language Models: A Comprehensive Surveycited by 234
  8. 2022FOSTER: Feature Boosting and Compression for Class-Incremental Learningcited by 229
  9. 2021New Insights on Reducing Abrupt Representation Change in Online Continual Learningcited by 219
  10. 2023Class-Incremental Learning: A Surveycited by 209
  11. 2024Boosting Continual Learning of Vision-Language Models via Mixture-of-Experts Adapterscited by 199
  12. 2023Continual Pre-training of Language Modelscited by 198
  13. 2022Patching open-vocabulary models by interpolating weightscited by 190
  14. 2023Robust Test-Time Adaptation in Dynamic Scenarioscited by 189
  15. 2022Dataset Condensation via Efficient Synthetic-Data Parameterizationcited by 188
  16. 2021Few-Shot Incremental Learning with Continually Evolved Classifierscited by 187
  17. 2023Revisiting Class-Incremental Learning with Pre-Trained Models: Generalizability and Adaptivity are All You Needcited by 184
  18. 2023Mitigating the Alignment Tax of RLHFcited by 183
  19. 2022Scaling Up Dataset Distillation to ImageNet-1K with Constant Memorycited by 181
  20. 2022Dataset Distillation using Neural Feature Regressioncited by 177
  21. 2025RL's Razor: Why Online Reinforcement Learning Forgets Lesscited by 176
  22. 2023RanPAC: Random Projections and Pre-trained Models for Continual Learningcited by 164
  23. 2022Fine-tuned Language Models are Continual Learnerscited by 156
  24. 2021A Unified Survey on Anomaly, Novelty, Open-Set, and Out-of-Distribution Detection: Solutions and Future Challengescited by 154
  25. 2022A Model or 603 Exemplars: Towards Memory-Efficient Class-Incremental Learningcited by 154
  26. 2021Graph Condensation for Graph Neural Networkscited by 150
  27. 2021Self-Supervised Models are Continual Learnerscited by 149
  28. 2021Training Networks in Null Space of Feature Covariance for Continual Learningcited by 143
  29. 2021Supervised Contrastive Replay: Revisiting the Nearest Class Mean Classifier in Online Class-Incremental Continual Learningcited by 141
  30. 2023Continual Diffusion: Continual Customization of Text-to-Image Diffusion with C-LoRAcited by 141
  31. 2023Continual Pre-Training of Large Language Models: How to (re)warm your model?cited by 137
  32. 2021An Empirical Investigation of the Role of Pre-training in Lifelong Learningcited by 134
  33. 2022Dataset Pruning: Reducing Training Data by Examining Generalization Influencecited by 133
  34. 2021Always Be Dreaming: A New Approach for Data-Free Class-Incremental Learningcited by 131
  35. 2022Forward Compatible Few-Shot Class-Incremental Learningcited by 127
  36. 2022Federated Class-Incremental Learningcited by 127
  37. 2023Dataset Distillation: A Comprehensive Reviewcited by 127
  38. 2023A Unified Continual Learning Framework with General Parameter-Efficient Tuningcited by 125

50 most cited of 2,333 All 2,333 (JSON)