Vision Transformer

FairViT: Fair Vision Transformer via Adaptive Masking
Vision Transformer (ViT) has achieved excellent performance and demonstrated its promising potential on various computer vision tasks. …
Bowei Tian, Ruijie Du, Yanning Shen
PDF Cite Code
FairViT: Fair Vision Transformer via Adaptive Masking
MEGATRON: Backdooring Vision Transformers with Invisible Triggers
Vision transformers have achieved impressive performance in various vision-related tasks, but their vulnerability to backdoor attacks …
Xueluan Gong, Bowei Tian, Meng Xue, Yanjiao Chen, Qian Wang, Mengyuan Sun
PDF Cite
MEGATRON: Backdooring Vision Transformers with Invisible Triggers