New CAM Method: FinerCAM #561
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
jacobgil
approved these changes
Mar 14, 2025
|
Thanks so much for the contribution, very nice idea and paper. |
|
I accidentally uploaded the wrong image here. Could you please help delete it? Sorry about that |
|
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Thank you, Jacob, for your excellent work on pytorch-gradcam.
This pull request introduces Finer-CAM, a new method that improves class activation mapping for fine-grained classification tasks. Our approach uses a weighted difference between the main category and comparison categories to suppress shared features and highlight discriminative details. This method is based on our recent paper, which has been accepted by CVPR 2025:
Finer-CAM.
Finer-CAM is implemented through the new classes
FinerWeightedTargetandFinerCAM. The design makes it easy to integrate with existing CAM methods while providing a clearer view of subtle differences between similar classes.I have also prepared a tutorial: Finer-CAM Tutorial to help you test this method more easily. Please let me know if you have any questions or suggestions.
Again, thank you for your wonderful work!