-
Notifications
You must be signed in to change notification settings - Fork 13
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
Autotune p_keep parameter for RISE #24
Comments
We need to chose some value for For images:When using 20 n_masks we got this p_keep bincount: [ 1 7 19 24 21 18 8 2] It seems 20 is not enough to have a good chance of getting a good p_keep as there is a l lot of variation in the chosen For text:When using 20 n_masks we got this p_keep bincount: [ 0 0 2 11 37 41 7 2] It seems 20 is not enough to have a good chance of getting a good p_keep. It seems 50 n_masks is enough here. |
We think that std of the probability of the predicted correct class on all masked instances of an image should be somewhere between 0.2 and 0.4. Under 0.1 we didn't see any good looking heatmaps. Between 0.1 and 0.2 we often saw some artifacts and strange blobs in the heatmaps. From 0.2 onwards we didn't see such randomish errors anymore. An std of 0.5 is possible in theory and will probably also be fine in terms of the resulting heatmap. Conclusion: at least std of 0.2.
Proposed algorithm:
The text was updated successfully, but these errors were encountered: