study0098

TAPADL

Code of "Robustifying Token Attention for Vision Transformers"

DyNCA

FaceAttack

SpatiotemporalAttack

Adversarial-Alignment

Scaling-up deep neural networks to improve their performance on ImageNet makes them more tolerant to adversarial attacks, but successful attacks on these models are misaligned with human perception.

18-RSS-PhysicalManipulation

Code supplement to the R:SS 2018 on Physical Manipulation

BDCI2018

Some code used in BDCI2018, Supply chain

BUAA_AI_Homework

HangWei

Robust-Vision-Transformer

The implementation of our paper: Towards Robust Vision Transformer (CVPR2022)

study0098/18-RSS-PhysicalManipulation

Code supplement to the R:SS 2018 on Physical Manipulation

study0098/BDCI2018

Some code used in BDCI2018, Supply chain

study0098/BUAA_AI_Homework

study0098/HangWei