latentspace
56f9f88906aebf4ad985aaec7fa01313-AuthorFeedback.pdf
Wethank the reviewers for their insightful comments and agree with all points related to clarity of the terminology,1 notation,andimagequality. We find R2's request for reporting image generation quality reasonable; although we stress that the objectives of20 this model was generation of disease maps (for which we show clear improvements) rather than image generation.21 These scores are not as good as the feature35 attribution (FA)maps generated byICAM'sgenerator network.