5 papers
Learning Dynamic Representations via An Optimally-Weighted Maximum Mean Discrepancy Optimization Framework for Continual Learning
KaiHui Huang, RunQing Wu, JinHui Sheng +4
Continual learning has emerged as a pivotal area of research, primarily due to its advantageous characteristic that allows models to persistently acquire and retain information. Ho…
Dynamic Dual Buffer with Divide-and-Conquer Strategy for Online Continual Learning
Congren Dai, Huichi Zhou, Jiahao Huang +5
Online Continual Learning (OCL) involves sequentially arriving data and is particularly challenged by catastrophic forgetting, which significantly impairs model performance. To add…
Self-Controlled Dynamic Expansion Model for Continual Learning
Runqing Wu, Kaihui Huang, Hanyi Zhang +1
Continual Learning (CL) epitomizes an advanced training paradigm wherein prior data samples remain inaccessible during the acquisition of new tasks. Numerous investigations have de…
Incrementally Learning Multiple Diverse Data Domains via Multi-Source Dynamic Expansion Model
Runqing Wu, Fei Ye, Qihe Liu +3
Continual Learning seeks to develop a model capable of incrementally assimilating new information while retaining prior knowledge. However, current research predominantly addresses…
Information-Theoretic Dual Memory System for Continual Learning
RunQing Wu, KaiHui Huang, HanYi Zhang +4
Continuously acquiring new knowledge from a dynamic environment is a fundamental capability for animals, facilitating their survival and ability to address various challenges. This…