Update in ipt.py (Explanation from perturbed images) - #11
Open
lorenzkautzsch wants to merge 1 commit into
Open
lorenzkautzsch wants to merge 1 commit into
lorenzkautzsch wants to merge 1 commit into
Conversation
Previously, the perturbed images were only used in metric score calculation, however localisation metrics for example do not consider the input image, but only the reference mask and the attribution. Therefore, the IPT only assesses the stability of the considered explanation methods. According to the paper, the explanations are regenerated on the perturbed images.
This file contains hidden or 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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Previously, the perturbed images were only used in metric score calculation, however localisation metrics for example do not consider input image, but only the reference mask and the attribution. @annahedstroem Therefore, the IPT only assesses the stability of the considered explanation methods. According to the paper, the explanations are regenerated on the perturbed images.