Skip to content
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

How the SVM detector is trained? #1

Open
machengcheng2016 opened this issue Jan 18, 2019 · 3 comments
Open

How the SVM detector is trained? #1

machengcheng2016 opened this issue Jan 18, 2019 · 3 comments

Comments

@machengcheng2016
Copy link

Hello! As discussed in your CVPR paper, there is a SVM detector in the test phase judging whether input image is an adversarial one. So my question is how the SVM model is pre-trained, and use what kind of samples to train it? I did not find a clue in your released code. May you kindly give your answer?

@JingWu321
Copy link

Hello! As discussed in your CVPR paper, there is a SVM detector in the test phase judging whether input image is an adversarial one. So my question is how the SVM model is pre-trained, and use what kind of samples to train it? I did not find a clue in your released code. May you kindly give your answer?

Hi! Have you solved this problem? I cannot see the SVM detector part in this code, either. It seems that this released code only show that they applied an adversarial training.

@machengcheng2016
Copy link
Author

Hello! As discussed in your CVPR paper, there is a SVM detector in the test phase judging whether input image is an adversarial one. So my question is how the SVM model is pre-trained, and use what kind of samples to train it? I did not find a clue in your released code. May you kindly give your answer?

Hi! Have you solved this problem? I cannot see the SVM detector part in this code, either. It seems that this released code only show that they applied an adversarial training.

Ehhh.. Nope.
I guess it is trivial to mention in the whole denoising process... Since there have already been many adversarial detection methods...

@JingWu321
Copy link

Hello! As discussed in your CVPR paper, there is a SVM detector in the test phase judging whether input image is an adversarial one. So my question is how the SVM model is pre-trained, and use what kind of samples to train it? I did not find a clue in your released code. May you kindly give your answer?

Hi! Have you solved this problem? I cannot see the SVM detector part in this code, either. It seems that this released code only show that they applied an adversarial training.

Ehhh.. Nope.
I guess it is trivial to mention in the whole denoising process... Since there have already been many adversarial detection methods...

Okay.
I think you are right.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants