mlsanityData to 7 Oct 2026

ACAE-REMIND for Online Continual Learning with Compressed Feature Replay

arXiv 2105.08595 ↗First posted 18 May 2021cs.CVcited by 12

Not on the map. Why?

Abstract (arXiv)

Online continual learning aims to learn from a non-IID stream of data from a number of different tasks, where the learner is only allowed to consider data once. Methods are typically allowed to use a limited buffer to store some of the images in the stream. Recently, it was found that feature replay, where an intermediate layer representation of the image is stored (or generated) leads to superior results than image replay, while requiring less memory. Quantized exemplars can further reduce the memory usage. However, a drawback of these methods is that they use a fixed (or very intransigent) backbone network. This significantly limits the learning of representations that can discriminate between all tasks. To address this problem, we propose an auxiliary classifier auto-encoder (ACAE) module for feature replay at intermediate layers with high compression rates. The reduced memory footprint per image allows us to save more exemplars for replay. In our experiments, we conduct task-agnostic evaluation under online continual learning setting and get state-of-the-art performance on ImageNet-Subset, CIFAR100 and CIFAR10 dataset.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 23 of its 36 references that are in the map. First posted on arXiv 18 May 2021.

Builds on

23 of 36 references.

References · 23

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
  3. 2017Billion-scale similarity search with GPUscited by 2,477
  4. 2016Learning without Forgettingcited by 2,465
  5. 2016iCaRL: Incremental Classifier and Representation Learningcited by 2,313
  6. 2017Gradient Episodic Memory for Continual Learningcited by 1,871
  7. 2017Continual Learning with Deep Generative Replaycited by 1,152
  8. 2018Experience Replay for Continual Learningcited by 1,074
  9. 2018Efficient Lifelong Learning with A-GEMcited by 1,044
  10. 2017PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruningcited by 882
  11. 2019Large Scale Incremental Learningcited by 727
  12. 2018Overcoming catastrophic forgetting with hard attention to the taskcited by 672
11 more
  1. 2019Gradient based sample selection for online continual learningcited by 568
  2. 2020Class-incremental learning: survey and performance evaluation on image classificationcited by 446
  3. 2019Online Continual Learning with Maximally Interfered Retrievalcited by 376
  4. 2016Expert Gate: Lifelong Learning with a Network of Expertscited by 369
  5. 2019REMIND Your Neural Network to Prevent Catastrophic Forgettingcited by 197
  6. 2020Using Hindsight to Anchor Past Knowledge in Continual Learningcited by 160
  7. 2018Towards Robust Evaluations of Continual Learningcited by 148
  8. 2020Generative Feature Replay For Class-Incremental Learningcited by 109
  9. 2020Memory-Efficient Incremental Learning Through Feature Adaptationcited by 107
  10. 2018Task Agnostic Continual Learning Using Online Variational Bayescited by 61
  11. 2020Ternary Feature Masks: zero-forgetting for task-incremental learningcited by 14

Built on by

Cited by year

Citing papers per year: 2022: 3; 2023: 4; 2024: 2; 2025: 3.

12 papers.

  1. 2023A Comprehensive Survey of Continual Learning: Theory, Method and Applicationcited by 860
  2. 2023SIESTA: Efficient Online Continual Learning with Sleepcited by 24
  3. 2022Model-Free Generative Replay for Lifelong Reinforcement Learning: Application to Starcraft-2cited by 11
  4. 2025Federated Class-Incremental Learning: A Hybrid Approach Using Latent Exemplars and Data-Free Techniques to Address Local and Global Forgettingcited by 9
  5. 2024Continual Learning with Neuromorphic Computing: Foundations, Methods, and Emerging Applicationscited by 7
  6. 2022System Design for an Integrated Lifelong Reinforcement Learning Agent for Real-Time Strategy Gamescited by 3
  7. 2023Remind of the Past: Incremental Learning with Analogical Promptscited by 3
  8. 2023Hadamard Domain Training with Integers for Class Incremental Quantized Learningcited by 3
  9. 2025Autoencoder-Based Hybrid Replay for Class-Incremental Learningcited by 3
  10. 2022Positive Pair Distillation Considered Harmful: Continual Meta Metric Learning for Lifelong Object Re-Identificationcited by 1
  11. 2025GaitAdapt: Continual Learning for Evolving Gait Recognitioncited by 1
  12. 2024FETCH: A Memory-Efficient Replay Approach for Continual Learning in Image Classificationcited by 0