3 papers
cs.LG2026
Pushing the Limits of Distillation-Based Continual Learning via Classifier-Proximal Lightweight Plugins
Zhiming Xu, Baile Xu, Jian Zhao +2
Continual learning requires models to learn continuously while preserving prior knowledge under evolving data streams. Distillation-based methods are appealing for retaining past k…
cs.CV2025
AdaAugment: A Tuning-Free and Adaptive Approach to Enhance Data Augmentation
Suorong Yang, Peijia Li, Xin Xiong +2
Data augmentation (DA) is widely employed to improve the generalization performance of deep models. However, most existing DA methods employ augmentation operations with fixed or r…
cs.LG2025
RL-Selector: Reinforcement Learning-Guided Data Selection via Redundancy Assessment
Suorong Yang, Peijia Li, Furao Shen +1
Modern deep architectures often rely on large-scale datasets, but training on these datasets incurs high computational and storage overhead. Real-world datasets often contain subst…