ACAE-REMIND for Online Continual Learning with Compressed Feature Replay
By Kai Wang, Luis Herranz, Joost van de Weijer. 2021
21 citations recorded by the source corpus.
Abstract 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.
Subfields: Efficiency & Compression, Meta & Continual Learning
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Efficiency & Compression
In Meta & Continual Learning
- Xingxing Zhang
- Liyuan Wang
- Hang Su
- Jun Zhu
- Simone Scardapane
- Valerio Marsocci
- Liyuan Wang
- Hongwei Yan
Citations in the corpus
- A Comprehensive Survey of Continual Learning: Theory, Method and Application (2023, background): “REMIND [155] and ACAEREMIND [426] instead fix the early layers of the feature extractor and reconstruct the intermediate representations to update the latter layers.”
- Model-Free Generative Replay for Lifelong Reinforcement Learning: Application to Starcraft-2 (2022, background): “Others have explored sophisticated strategies for experience replay in DQN (e.g. Isele & Cosgun, 2018; Riemer et al., 2019; Wang et al., 2021; Caccia et al., 2020; Zhang & Sutton, 2017; Schaul et al., 2015) in lifelong RL, but these are not generative in nature.”