4 papers
Online Continual Learning with Dynamic Label Hierarchies
Xinrui Wang, Shao-Yuan Li, BartÅomiej Twardowski +2
Online Continual Learning (OCL) aims to learn from endless non\text{-}stationary data streams, yet most existing methods assume a flat label space and overlook the hierarchical org…
DORA: Dynamic Online Reinforcement Agent for Token Merging in Vision Transformers
Kaixuan He, Song Chen, Yi Kang
Vision Transformers (ViTs) incur significant computational overhead due to the quadratic complexity of self-attention relative to the token sequence length. While existing token re…
Global Pre-fixing, Local Adjusting: A Simple yet Effective Contrastive Strategy for Continual Learning
Jia Tang, Xinrui Wang, Songcan Chen
Continual learning (CL) involves acquiring and accumulating knowledge from evolving tasks while alleviating catastrophic forgetting. Recently, leveraging contrastive loss to constr…
Cut out and Replay: A Simple yet Versatile Strategy for Multi-Label Online Continual Learning
Xinrui Wang, Shao-yuan Li, Jiaqiang Zhang +1
Multi-Label Online Continual Learning (MOCL) requires models to learn continuously from endless multi-label data streams, facing complex challenges including persistent catastrophi…