DLight

FT-CLIP. CLIP Itself is a Strong Fine-tuner: Achieving 85.7% and 88.0% Top-1 Accuracy with ViT-B and ViT-L on ImageNet

ICT_DeepFake. Python

BootMAE. ECCV2022,Bootstrapped Masked Autoencoders for Vision BERT Pretraining

MaskCLIP.

GreedyFool. GreedyFool (NIPS2020) official code for saprse adversarial attack

Super_Pix_Adv. Offical implemention of Robust Superpixel-Guided Attentional Adversarial Attack (CVPR2020)

MAN_adversarial. ICCV2019 Once a MAN: Towards Multi-target Attack via Learning Multi-target Adversarial Network Once