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

The effect of backbone models (resnet) #71

Open
pencilzhang opened this issue Jun 28, 2021 · 3 comments
Open

The effect of backbone models (resnet) #71

pencilzhang opened this issue Jun 28, 2021 · 3 comments

Comments

@pencilzhang
Copy link

Hi Richard,
Thanks for your great work!

I noticed that you reported the performance comparisons of alexnet, vgg, and squeezenet.
I am wondering if you also played with resnet? If yes, did you get the same conclusion as showed in the paper?

Thanks!
Jun

@richzhang
Copy link
Owner

We have some experiments in suppmat (Figure 12), actually observing worse correlation with resnet. Interestingly, this is consistent with some results in neuroscience on correlating IT responses with deep network responses https://youtu.be/ilbbVkIhMgo?t=2220

@pencilzhang
Copy link
Author

We have some experiments in suppmat (Figure 12), actually observing worse correlation with resnet. Interestingly, this is consistent with some results in neuroscience on correlating IT responses with deep network responses https://youtu.be/ilbbVkIhMgo?t=2220

Thanks for your response. I read the cvpr version and missed the suppl things. Also thanks for your neuroscience talk link.

@MalharJ
Copy link

MalharJ commented Jul 5, 2021

How can I experiment with resnet models? The library currently supports only vgg, alexnet and squeezenet models.

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

3 participants