# Knowledge Capture and Replay for Continual Learning

arXiv: https://arxiv.org/abs/2012.06789 · HTML: https://mlsanity.com/paper/2012.06789/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Dec 2020.

## Built on by (most cited first, 7 of 7)

- [A Comprehensive Survey of Continual Learning: Theory, Method and Application](https://mlsanity.com/paper/2302.00487/) (2023)
- [ProtoDepth: Unsupervised Continual Depth Completion with Prototypes](https://mlsanity.com/paper/2503.12745/) (2025)
- [UnCLe: Benchmarking Unsupervised Continual Learning for Depth Completion](https://mlsanity.com/paper/2410.18074/) (2024)
- [Looking through the past: better knowledge retention for generative replay in continual learning](https://mlsanity.com/paper/2309.10012/) (2023)
- [Robust Continual Learning through a Comprehensively Progressive Bayesian Neural Network](https://mlsanity.com/paper/2202.13369/) (2022)
- [ReFu: Recursive Fusion for Exemplar-Free 3D Class-Incremental Learning](https://mlsanity.com/paper/2409.12326/) (2024)
- [Continual learning via probabilistic exchangeable sequence modelling](https://mlsanity.com/paper/2503.20725/) (2025)

## Abstract (arXiv)

Deep neural networks have shown promise in several domains, and the learned data (task) specific information is implicitly stored in the network parameters. Extraction and utilization of encoded knowledge representations are vital when data is no longer available in the future, especially in a continual learning scenario. In this work, we introduce em flashcards, which are visual representations that em capture the encoded knowledge of a network as a recursive function of predefined random image patterns. In a continual learning scenario, flashcards help to prevent catastrophic forgetting and consolidating knowledge of all the previous tasks. Flashcards need to be constructed only before learning the subsequent task, and hence, independent of the number of tasks trained before. We demonstrate the efficacy of flashcards in capturing learned knowledge representation (as an alternative to the original dataset) and empirically validate on a variety of continual learning tasks: reconstruction, denoising, task-incremental learning, and new-instance learning classification, using several heterogeneous benchmark datasets. Experimental evidence indicates that: (i) flashcards as a replay strategy is  em task agnostic, (ii) performs better than generative replay, and (iii) is on par with episodic replay without additional memory overhead.