Yeez-lee

Autoattack and APGDT

3

Hi, I am a primary learner and still feel little bit confused about the autoattack and target apgdt. (1) For the standard autoattack, do all images are attacked by 4...

Structural downsampling and static token sparsification

3

Hi, it's a quite solid and promising work but I have some questions. (1) In the paper, you perform an average pooling with kernel size 2 × 2 after the...

Different Pre-trained Models

1

Dear authors, Thanks for sharing this great work! I want to try different training strategies to train my own ResNet32 or VGG16 but there are some bugs because of your...

Hi, thanks for the sharing codes and it's a solid work. But I have some questions about **_Adaptive Attacks_**. (1) What's your adaptive attacks based on? CW, PGD or FGSM?...

Visualize the similar image pairs

1

Hi, Thanks for your efforts. I want to ask some questions about visualizations. Can you provide some codes on how to visualize the similar image pairs (like Figure 1 and...

Training Settings

3

Hi, I am curious about your MDTv2_s2 settings. What is your lr_anneal_steps? Should I set it to 0? And how can I control the training steps? For example, how can...