Batch-level Experience Replay with Review for Continual Learning

By Zheda Mai, Hyunwoo J. Kim, Jihwan Jeong, Scott Sanner. 2020

18 citations recorded by the source corpus.

Continual learning is a branch of deep learning that seeks to strike a balance between learning stability and plasticity. The CVPR 2020 CLVision Continual Learning for Computer Vision challenge is dedicated to evaluating and advancing the current state-of-the-art continual learning methods using the CORe50 dataset with three different continual learning scenarios. This paper presents our approach, called Batch-level Experience Replay with Review, to this challenge. Our team achieved the 1'st place in all three scenarios out of 79 participated teams. The codebase of our implementation is publicly available at this https URL

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Online Continual Learning in Image Classification: An Empirical Survey (2021, methodology): “We find that all tricks are beneficial and when augmented with the ”review” trick [25] and a nearest class mean (NCM) classifier [8], MIR produces performance levels that bring online CL much closer to its ultimate goal of matching offline training.”
CVPR 2020 Continual Learning in Computer Vision Competition: Approaches, Results, Current Challenges and Future Directions (2020, background): “The details of their implementation can be found in (Mai et al., 2020) Algorithm The use of episodic memories in continual learning is an efﬁcient way to prevent the phenomenon of catastrophic forgetting .”
A TinyML Platform for On-Device Continual Learning With Quantized Latent Replays (2021, background): “track (the same scenario considered in our work) [17], which is evaluated in terms of test accuracy but also memory and computation requirements, scores 91% by replaying image data.”