most citedNTIRE 2022 Challenge on High Dynamic Range Imaging: Methods and Results

11 citations · 14 across the 3 of their papers we have counts for

collaborators
Showing cs.LGShow all

1 paper · 1 filter

cs.LG2022★ 2 cited

Fast Adversarial Training with Noise Augmentation: A Unified Perspective on RandStart and GradAlign

Axi Niu, Kang Zhang, Chaoning Zhang +4

PGD-based and FGSM-based are two popular adversarial training (AT) approaches for obtaining adversarially robust models. Compared with PGD-based AT, FGSM-based one is significantly…