mlsanityData to 7 Oct 2026

Practical Recommendations for Replay-based Continual Learning Methods

arXiv 2203.10317 ↗First posted 19 Mar 2022cs.LGcited by 16

Not on the map. Why?

Abstract (arXiv)

Continual Learning requires the model to learn from a stream of dynamic, non-stationary data without forgetting previous knowledge. Several approaches have been developed in the literature to tackle the Continual Learning challenge. Among them, Replay approaches have empirically proved to be the most effective ones. Replay operates by saving some samples in memory which are then used to rehearse knowledge during training in subsequent tasks. However, an extensive comparison and deeper understanding of different replay implementation subtleties is still missing in the literature. The aim of this work is to compare and analyze existing replay-based strategies and provide practical recommendations on developing efficient, effective and generally applicable replay-based strategies. In particular, we investigate the role of the memory size value, different weighting policies and discuss about the impact of data augmentation, which allows reaching better performance with lower memory sizes.

Key facts. Cited by 16 papers in the map (data through 7 Oct 2026). Builds on 19 of its 34 references that are in the map. First posted on arXiv 19 Mar 2022.

Builds on

19 of 34 references.

References · 19

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2016iCaRL: Incremental Classifier and Representation Learningcited by 2,313
  3. 2018Continual Lifelong Learning with Neural Networks: A Reviewcited by 1,313
  4. 2017Continual Learning with Deep Generative Replaycited by 1,152
  5. 2020Dark Experience for General Continual Learning: a Strong, Simple Baselinecited by 895
  6. 2019Data Shapley: Equitable Valuation of Data for Machine Learningcited by 617
  7. 2019Gradient based sample selection for online continual learningcited by 568
  8. 2018Learning to Learn without Forgetting by Maximizing Transfer and Minimizing Interferencecited by 511
  9. 2019Online Continual Learning with Maximally Interfered Retrievalcited by 376
  10. 2017CORe50: a New Dataset and Benchmark for Continuous Object Recognitioncited by 287
  11. 2021Online Continual Learning in Image Classification: An Empirical Surveycited by 242
  12. 2018Re-evaluating Continual Learning Scenarios: A Categorization and Case for Strong Baselinescited by 228
7 more
  1. 2021Avalanche: an End-to-End Library for Continual Learningcited by 124
  2. 2018Don't forget, there is more than forgetting: new metrics for Continual Learningcited by 113
  3. 2020Rethinking Experience Replay: a Bag of Tricks for Continual Learningcited by 94
  4. 2016Understanding data augmentation for classification: when to warp?cited by 74
  5. 2020CVPR 2020 Continual Learning in Computer Vision Competition: Approaches, Results, Current Challenges and Future Directionscited by 26
  6. 2019Efficient Continual Learning in Neural Networks with Embedding Regularizationcited by 20
  7. 2021Ex-Model: Continual Learning from a Stream of Trained Modelscited by 11

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 4; 2023: 4; 2024: 4; 2025: 2; 2026: 2.

16 papers.

Sort:

By area:

  1. 2022Continual Pre-Training Mitigates Forgetting in Language and Visioncited by 82
  2. 2024Unveiling the Anomalies in an Ever-Changing World: A Benchmark for Pixel-Level Anomaly Detection in Continual Learningcited by 13
  3. 2023Just a Glimpse: Rethinking Temporal Information for Video Continual Learningcited by 10
  4. 2022Memory Population in Continual Learning via Outlier Eliminationcited by 9
  5. 2022Continual Learning Approaches for Anomaly Detectioncited by 9
  6. 2023Design Principles for Lifelong Learning AI Acceleratorscited by 9
  7. 2025Forget Forgetting: Continual Learning in a World of Abundant Memorycited by 9
  8. 2022Progressive Latent Replay for efficient Generative Rehearsalcited by 3
  9. 2023Exploring Data Redundancy in Real-world Image Classification through Data Selectioncited by 3
  10. 2024One Step Learning, One Step Reviewcited by 2
  11. 2024Adaptive Hyperparameter Optimization for Continual Learning Scenarioscited by 2
  12. 2025H2C: Hippocampal Circuit-inspired Continual Learning for Lifelong Trajectory Prediction in Autonomous Drivingcited by 2
4 more
  1. 2023Architect, Regularize and Replay (ARR): a Flexible Hybrid Approach for Continual Learningcited by 1
  2. 2024Continual Learning from Simulated Interactions via Multitask Prospective Rehearsal for Bionic Limb Behavior Modelingcited by 1
  3. 2026Neural Network Optimization Reimagined: Decoupled Techniques for Scratch and Fine-Tuningcited by 0
  4. 2026An Empirical Analysis of Continual Learning for Heterogeneous Medical Visual Question Answeringcited by 0