New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Questions about equation (1) and (3) #18
Comments
Hi @YeRen123455, Sorry for the confusion. [16, 28] manipulate images with perturbation obtained by "Loss", but our method manipulates with "Logit". Since decreasing the logit value increases the loss value, Eq (1) and [16] are conceptually the same. Thanks |
@jbeomlee93 Thanks a lot! I get it. |
We perform adversarial climbing on training images, and the trained model already produces very small loss values for the training images. As such, loss-based adversarial climbing rarely manipulates images. |
@jbeomlee93 Thanks for your answer! Sorry for disturbing you again. I still have two questions about the released code. (2) Can you share the code of "SEAM+AdvCAM" with me. I try to reproduce it by myself but the performance is not good as yours. My email address is liboyang20@nudt.edu.cn |
Hi @jbeomlee93 I have some questions for the equations of you paper. That is:
1. For equation(1), the paper[16] uses x' = x + gradient to adversarial attack the input image (i.e., X) and finally generate the image Xadv, which is opposited to your equation (1) (i.e., x' = x - gradient ).
2. For equation(3), the paper[28] uses iter(x' = x + gradient) to represents the adversarial attack process, which is same to equation (3)(i.e., x' = x + gradient ). I think adversarial climbing should be opposited to the adversarial attack.
Sincerely waiting for your reply !
The text was updated successfully, but these errors were encountered: