Looking Through the Past: Better Knowledge Retention for Generative Replay in Continual Learning
In this work, we improve the generative replay in a continual learning setting to perform well on challenging scenarios. Because of the growing complexity of continual learning tasks, it is becoming more popular, to apply the generative replay technique in the feature space instead of image space. N...
Main Authors: | Valeriya Khan, Sebastian Cygert, Kamil Deja, Tomasz Trzcinski, Bartlomiej Twardowski |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2024-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/10474374/ |
Similar Items
-
MixER: Mixup-Based Experience Replay for Online Class-Incremental Learning
by: Won-Seon Lim, et al.
Published: (2024-01-01) -
Enhanced Off-Policy Reinforcement Learning With Focused Experience Replay
by: Seung-Hyun Kong, et al.
Published: (2021-01-01) -
A model of hippocampal replay driven by experience and environmental structure facilitates spatial learning
by: Nicolas Diekmann, et al.
Published: (2023-03-01) -
THE FUTURE, THE CRISIS, AND THE FUTURE OF REPLAY STORY
by: Eleonora Teresa Imbierowicz
Published: (2021-06-01) -
Deep Deterministic Policy Gradient with Episode Experience Replay
by: ZHANG Jian-hang, LIU Quan
Published: (2021-10-01)