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.

Sign up for GitHub

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

Jump to bottom

About the results of MT-ConFT #2

Open
lovelyqian opened this issue Jan 20, 2022 · 1 comment
Open

About the results of MT-ConFT #2

lovelyqian opened this issue Jan 20, 2022 · 1 comment

Comments

@lovelyqian
Copy link

Hi, first thanks for your work and codes!

Under the 5-way-5-shot setting taking CUB as the target dataset, I got the results of 69.91 +- 0.75% and 69.94 +- 0.71% of ''ConFT'' and ''MT-ConFT'' by using the given "conft.sh" and "mt_conft.sh", respectively. However, the results of 'MT-ConFT'' in the paper is 74.45%. Could you tell me if there is something wrong with my experiments?
@fikry102
Copy link

I got the result of 70.68 +- 0.72 for "MT-ConFT". But it is still much lower than "74.45 ± 0.71".
Do you solve this problem?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@lovelyqian @fikry102