4 papers · 1 filter
The Power of Many: Synergistic Unification of Diverse Augmentations for Efficient Adversarial Robustness
Wang Yu-Hang, Shiwei Li, Jianxiang Liao +3
Adversarial perturbations pose a significant threat to deep learning models. Adversarial Training (AT), the predominant defense method, faces challenges of high computational costs…
AttriPrompt: Dynamic Prompt Composition Learning for CLIP
Qiqi Zhan, Shiwei Li, Qingjie Liu +1
The evolution of prompt learning methodologies has driven exploration of deeper prompt designs to enhance model performance. However, current deep text prompting approaches suffer…
ONER: Online Experience Replay for Incremental Anomaly Detection
Yizhou Jin, Jiahui Zhu, Guodong Wang +5
Incremental anomaly detection aims to sequentially identify defects in industrial product lines but suffers from catastrophic forgetting, primarily due to knowledge overwriting dur…
DSD-DA: Distillation-based Source Debiasing for Domain Adaptive Object Detection
Yongchao Feng, Shiwei Li, Yingjie Gao +4
Though feature-alignment based Domain Adaptive Object Detection (DAOD) methods have achieved remarkable progress, they ignore the source bias issue, i.e., the detector tends to acq…