# Practical Recommendations for Replay-based Continual Learning Methods

arXiv: https://arxiv.org/abs/2203.10317 · HTML: https://mlsanity.com/paper/2203.10317/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 34 references that are in the map.
- First posted on arXiv 19 Mar 2022.

## Builds on (most cited first, 19 of 19)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016)
- [Continual Lifelong Learning with Neural Networks: A Review](https://mlsanity.com/paper/1802.07569/) (2018)
- [Continual Learning with Deep Generative Replay](https://mlsanity.com/paper/1705.08690/) (2017)
- [Dark Experience for General Continual Learning: a Strong, Simple Baseline](https://mlsanity.com/paper/2004.07211/) (2020)
- [Data Shapley: Equitable Valuation of Data for Machine Learning](https://mlsanity.com/paper/1904.02868/) (2019)
- [Gradient based sample selection for online continual learning](https://mlsanity.com/paper/1903.08671/) (2019)
- [Learning to Learn without Forgetting by Maximizing Transfer and Minimizing Interference](https://mlsanity.com/paper/1810.11910/) (2018)
- [Online Continual Learning with Maximally Interfered Retrieval](https://mlsanity.com/paper/1908.04742/) (2019)
- [CORe50: a New Dataset and Benchmark for Continuous Object Recognition](https://mlsanity.com/paper/1705.03550/) (2017)
- [Online Continual Learning in Image Classification: An Empirical Survey](https://mlsanity.com/paper/2101.10423/) (2021)
- [Re-evaluating Continual Learning Scenarios: A Categorization and Case for Strong Baselines](https://mlsanity.com/paper/1810.12488/) (2018)
- [Avalanche: an End-to-End Library for Continual Learning](https://mlsanity.com/paper/2104.00405/) (2021)
- [Don't forget, there is more than forgetting: new metrics for Continual Learning](https://mlsanity.com/paper/1810.13166/) (2018)
- [Rethinking Experience Replay: a Bag of Tricks for Continual Learning](https://mlsanity.com/paper/2010.05595/) (2020)
- [Understanding data augmentation for classification: when to warp?](https://mlsanity.com/paper/1609.08764/) (2016)
- [CVPR 2020 Continual Learning in Computer Vision Competition: Approaches, Results, Current Challenges and Future Directions](https://mlsanity.com/paper/2009.09929/) (2020)
- [Efficient Continual Learning in Neural Networks with Embedding Regularization](https://mlsanity.com/paper/1909.03742/) (2019)
- [Ex-Model: Continual Learning from a Stream of Trained Models](https://mlsanity.com/paper/2112.06511/) (2021)

## Built on by (most cited first, 16 of 16)

- [Continual Pre-Training Mitigates Forgetting in Language and Vision](https://mlsanity.com/paper/2205.09357/) (2022)
- [Unveiling the Anomalies in an Ever-Changing World: A Benchmark for Pixel-Level Anomaly Detection in Continual Learning](https://mlsanity.com/paper/2403.15463/) (2024)
- [Forget Forgetting: Continual Learning in a World of Abundant Memory](https://mlsanity.com/paper/2502.07274/) (2025)
- [Just a Glimpse: Rethinking Temporal Information for Video Continual Learning](https://mlsanity.com/paper/2305.18418/) (2023)
- [Memory Population in Continual Learning via Outlier Elimination](https://mlsanity.com/paper/2207.01145/) (2022)
- [Continual Learning Approaches for Anomaly Detection](https://mlsanity.com/paper/2212.11192/) (2022)
- [Design Principles for Lifelong Learning AI Accelerators](https://mlsanity.com/paper/2310.04467/) (2023)
- [Progressive Latent Replay for efficient Generative Rehearsal](https://mlsanity.com/paper/2207.01562/) (2022)
- [Exploring Data Redundancy in Real-world Image Classification through Data Selection](https://mlsanity.com/paper/2306.14113/) (2023)
- [One Step Learning, One Step Review](https://mlsanity.com/paper/2401.10962/) (2024)
- [Adaptive Hyperparameter Optimization for Continual Learning Scenarios](https://mlsanity.com/paper/2403.07015/) (2024)
- [H2C: Hippocampal Circuit-inspired Continual Learning for Lifelong Trajectory Prediction in Autonomous Driving](https://mlsanity.com/paper/2508.01158/) (2025)
- [Architect, Regularize and Replay (ARR): a Flexible Hybrid Approach for Continual Learning](https://mlsanity.com/paper/2301.02464/) (2023)
- [Continual Learning from Simulated Interactions via Multitask Prospective Rehearsal for Bionic Limb Behavior Modeling](https://mlsanity.com/paper/2405.01114/) (2024)
- [Neural Network Optimization Reimagined: Decoupled Techniques for Scratch and Fine-Tuning](https://mlsanity.com/paper/2604.22838/) (2026)
- [An Empirical Analysis of Continual Learning for Heterogeneous Medical Visual Question Answering](https://mlsanity.com/paper/2607.12048/) (2026)

## 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.