Where's the dissim term on the loss? about deep-learning-paper-review-and-practice HOT 2 CLOSED

Thank you for the good question.

I didn't use the Dissim term, because my code is a 1-channel attack version. So, the output of the Dissim function is always 0.
The author of the original paper mentioned that the 1-channel attack forces the values of each channel to have the same value.

In the source code, the get_ct() function is used to duplicate the values of a single channel into the values of 3-channels (r, g, b).
The 1-channel attack is more constrained, it might be weaker than the 3-channel attack. But the perturbation of the 1-channel attack tends to seem like a more natural shadow.

Best regards,
Dongbin Na

from deep-learning-paper-review-and-practice.

Thanks! I missed it, this is the 1-channel attack!

from deep-learning-paper-review-and-practice.