IEEE

Toward Enhanced Adversarial Robustness Generalization in Object Detection: Feature Disentangled Domain Adaptation for Adversarial Training

Abstract: Recent research has shown that deep learning models are likely to make incorrect predictions even when exposed to minor perturbations. To address this, training models on adversarial ...
IEEE

Mitigating Missing Feature Channels at Inference Stage: Test-Time Adaptation Through Self-Training With Data Imputation

Abstract: The robustness of deep learning model can be compromised by out-of-distribution (OOD) testing data. Test-time adaptation (TTA) emerges as an efficient method to mitigate the distribution gap ...