15825aee15eb335cc13f9b559f166ee8-AuthorFeedback.pdf

We are not certain we understood this criticism correctly. We use a diversity penalty (L113-115) in Generative MIR. In ER-MIR, diversity is enforced via sampling prior to applying the criterion (L102-104). We now extend our ER-MIR experiments to Mini-ImageNet split. Over 20 runs we obtain an accuracy of 26.4% We emphasize our work's aim was to determine if the In terms of memory consumption it is the same as ER with equivalent buffer.