2 papers
cs.LG2026
SAMix: Calibrated and Accurate Continual Learning via Sphere-Adaptive Mixup and Neural Collapse
Trung-Anh Dang, Vincent Nguyen, Ngoc-Son Vu +1
While most continual learning methods focus on mitigating forgetting and improving accuracy, they often overlook the critical aspect of network calibration, despite its importance.…
cs.CV2024
Memory-efficient Continual Learning with Neural Collapse Contrastive
Trung-Anh Dang, Vincent Nguyen, Ngoc-Son Vu +1
Contrastive learning has significantly improved representation quality, enhancing knowledge transfer across tasks in continual learning (CL). However, catastrophic forgetting remai…