Closed YeRen123455 closed 2 years ago
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. Since the image label is available, why don't you use "LOSS" to manipulate the images.
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. (1) In obtain_CAM_masking_super_pixel.py. Since you have used grad-cam to generate the class activation map(i.e., CAM), why don't you use resnet50.py with grad-cam to generate outputs. Actually, you used resnet50_cam.py with grad-cam to generate the outputs.
(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: