MixER: Mixup-based Experience Replay for Online Class-Incremental Learning
Published in IEEE Access, 2024
Authors: Wonseon Lim, Yi Zhou, Dae-Won Kim, Jaesung Lee
We introduce MixER, a mixup-based experience replay technique that combines memory samples and current-task samples to alleviate catastrophic forgetting in online class-incremental learning.
Recommended citation: W. Lim, Y. Zhou, D. Kim, J. Lee. (2024). "MixER: Mixup-based Experience Replay for Online Class-Incremental Learning." IEEE Access.
Download Paper