Appendixfor" Self-InterpretableModelwith TransformationEquivariant Interpretation "

Please refer to the Appendix 5 for details. Besides, in order to balance the classification loss and the transformation loss we set the scalar factor to beλ = 5 throughoutthetrainingphase. Here the first rows are the untransformed and the transformed images, while the second rows are the corresponding interpretations. This is a supplement toFigure 1 in the main body of the paper. And also there are perturbation methods such as randomized input sampling (RISE) [8] and extremal perturbation (EP) [2].