mlsanityData to 14 Oct 2026

ACIL: Analytic Class-Incremental Learning with Absolute Memorization and Privacy Protection

arXiv 2205.14922 ↗First posted 30 May 2022cs.LG cs.CVcited by 57

Not on the map. Why?

Abstract (arXiv)

Class-incremental learning (CIL) learns a classification model with training data of different classes arising progressively. Existing CIL either suffers from serious accuracy loss due to catastrophic forgetting, or invades data privacy by revisiting used exemplars. Inspired by linear learning formulations, we propose an analytic class-incremental learning (ACIL) with absolute memorization of past knowledge while avoiding breaching of data privacy (i.e., without storing historical data). The absolute memorization is demonstrated in the sense that class-incremental learning using ACIL given present data would give identical results to that from its joint-learning counterpart which consumes both present and historical samples. This equality is theoretically validated. Data privacy is ensured since no historical data are involved during the learning process. Empirical validations demonstrate ACIL's competitive accuracy performance with near-identical results for various incremental task settings (e.g., 5-50 phases). This also allows ACIL to outperform the state-of-the-art methods for large-phase scenarios (e.g., 25 and 50 phases).

Key facts. Cited by 57 papers in the map (data through 14 Oct 2026). Builds on 17 of its 33 references that are in the map. First posted on arXiv 30 May 2022.

Builds on

17 of 33 references.

References · 17

  1. 2016Overcoming catastrophic forgetting in neural networkscited by 4,787
  2. 2016Learning without Forgettingcited by 2,496
  3. 2016iCaRL: Incremental Classifier and Representation Learningcited by 2,333
  4. 2017Continual Learning with Deep Generative Replaycited by 1,158
  5. 2019Large Scale Incremental Learningcited by 732
  6. 2018End-to-End Incremental Learningcited by 597
  7. 2021DER: Dynamically Expandable Representation for Class Incremental Learningcited by 355
  8. 2020Semantic Drift Compensation for Class-Incremental Learningcited by 241
  9. 2020Mnemonics Training: Multi-Class Incremental Learning without Forgettingcited by 221
  10. 2019Class-incremental Learning via Deep Model Consolidationcited by 173
  11. 2020Adaptive Aggregation Networks for Class-Incremental Learningcited by 149
  12. 2018Rotate your Networks: Better Weight Consolidation and Less Catastrophic Forgettingcited by 127
5 more
  1. 2020A Comprehensive Study of Class Incremental Learning Algorithms for Visual Taskscited by 107
  2. 2016Less-forgetting Learning in Deep Neural Networkscited by 97
  3. 2018Memory Replay GANs: learning to generate images from new categories without forgettingcited by 77
  4. 2018Learning from the Kernel and the Range Spacecited by 9
  5. 2018Stacking-Based Deep Neural Network: Deep Analytic Network for Pattern Classificationcited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 16; 2025: 19; 2026: 21.

57 papers.

Sort:

By area:

  1. 2023Class-Incremental Learning: A Surveycited by 209
  2. 2024Continual Learning with Pre-Trained Models: A Surveycited by 154
  3. 2024Expandable Subspace Ensemble for Pre-Trained Model-Based Class-Incremental Learningcited by 117
  4. 2024GACL: Exemplar-Free Generalized Analytic Continual Learningcited by 22
  5. 2024Happy: A Debiased Learning Framework for Continual Generalized Category Discoverycited by 18
  6. 2024Advancing Cross-domain Discriminability in Continual Learning of Vision-Language Modelscited by 15
  7. 2024Task-recency bias strikes back: Adapting covariances in Exemplar-Free Class Incremental Learningcited by 14
  8. 2025Mixture of Noise for Pre-Trained Model-Based Class-Incremental Learningcited by 14
  9. 2024Locality Sensitive Sparse Encoding for Learning World Models Onlinecited by 12
  10. 2024F-OAL: Forward-only Online Analytic Learning with Fast Training and Low Memory Footprint in Class Incremental Learningcited by 12
  11. 2024AFL: A Single-Round Analytic Approach for Federated Learning with Pre-trained Modelscited by 11
  12. 2025ZeroFlow: Overcoming Catastrophic Forgetting is Easier than You Thinkcited by 9
38 more
  1. 2024AIR: Analytic Imbalance Rectifier for Continual Learningcited by 8
  2. 2024LoRanPAC: Low-rank Random Features and Pre-trained Models for Bridging Theory and Practice in Continual Learningcited by 8
  3. 2025On the Discrimination and Consistency for Exemplar-Free Class Incremental Learningcited by 8
  4. 2025Semantic Shift Estimation via Dual-Projection and Classifier Reconstruction for Exemplar-Free Class-Incremental Learningcited by 7
  5. 2025AnaCP: Toward Upper-Bound Continual Learning via Analytic Contrastive Projectioncited by 7
  6. 2024REAL: Representation Enhanced Analytic Learning for Exemplar-free Class-incremental Learningcited by 6
  7. 2024Analytic Continual Test-Time Adaptation for Multi-Modality Corruptioncited by 5
  8. 2024Online Analytic Exemplar-Free Continual Learning with Large Models for Imbalanced Autonomous Driving Taskcited by 4
  9. 2026Exact Federated Continual Unlearning for Ridge Heads on Frozen Foundation Modelscited by 4
  10. 2026Enhancing Pretrained Model-based Continual Representation Learning via Guided Random Projectioncited by 4
  11. 2025Global Convergence of Continual Learning on Non-IID Datacited by 3
  12. 2025Towards Efficient and Exact Forgetting Services in Pre-Trained-Model-based Continual Learningcited by 3
  13. 2025AFCL: Analytic Federated Continual Learning for Spatio-Temporal Invariance of Non-IID Datacited by 3
  14. 2025EFC++: Elastic Feature Consolidation with Prototype Re-balancing for Cold Start Exemplar-free Incremental Learningcited by 2
  15. 2025Analytic Subspace Routing: How Recursive Least Squares Works in Continual Learning of Large Language Modelcited by 2
  16. 2025Parameter Importance-Driven Continual Learning for Foundation Modelscited by 2
  17. 2026FlyPrompt: Brain-Inspired Random-Expanded Routing with Temporal-Ensemble Experts for General Continual Learningcited by 2
  18. 2025Enhancing Federated Class-Incremental Learning via Spatial-Temporal Statistics Aggregationcited by 1
  19. 2025CIFNet: An Analytic Neural Learning Framework for Efficient and Calibrated Class-Incremental Learningcited by 1
  20. 2026DeepAFL: Deep Analytic Federated Learningcited by 1
  21. 2026Analytic Drift Resister for Non-Exemplar Continual Graph Learningcited by 1
  22. 2024FACT: Feature Adaptive Continual-learning Tracker for Multiple Object Trackingcited by 0
  23. 2024ReFu: Recursive Fusion for Exemplar-Free 3D Class-Incremental Learningcited by 0
  24. 2025Gradient-Free Continual Learningcited by 0
  25. 2025Audio-Visual Class-Incremental Learning for Fish Feeding intensity Assessment in Aquaculturecited by 0
  26. 2025Mathematics of Continual Learningcited by 0
  27. 2025Confounder-Free Continual Learning via Recursive Feature Normalizationcited by 0
  28. 2025FedHiP: Heterogeneity-Invariant Personalized Federated Learning Through Closed-Form Solutionscited by 0
  29. 2025Closing the Oracle Gap: Increment Vector Transformation for Class Incremental Learningcited by 0
  30. 2026Analytic Incremental Learning For Sound Source Localization With Imbalance Rectificationcited by 0
  31. 2026Advancing Analytic Class-Incremental Learning through Vision-Language Calibrationcited by 0
  32. 2026Bi-CRCL: Bidirectional Conservative-Radical Complementary Learning with Pre-trained Foundation Models for Class-incremental Medical Image Analysiscited by 0
  33. 2026MIST: Reliable Streaming Decision Trees for Online Class-Incremental Learning via McDiarmid Boundcited by 0
  34. 2026Online Continual Learning with Dynamic Label Hierarchiescited by 0
  35. 2026Non-Forgetting Knowledge Allocation with Bi-level Competition for Class-Incremental Learningcited by 0
  36. 2026Accurate and Resource-Efficient Federated Continual Learningcited by 0
  37. 2026Geometry-Anchored Transport Framework for Exemplar-Free Class-Incremental Learningcited by 0
  38. 2026Data-Free Reservoir Features for Efficient Long-Horizon Cold-Start Continual Learningcited by 0

50 most cited of 57 All 57 (JSON)