ProtoPShare: Prototype Sharing for Interpretable Image Classification and Similarity Discovery

11/29/2020
by   Dawid Rymarczyk, et al.
0

In this paper, we introduce ProtoPShare, a self-explained method that incorporates the paradigm of prototypical parts to explain its predictions. The main novelty of the ProtoPShare is its ability to efficiently share prototypical parts between the classes thanks to our data-dependent merge-pruning. Moreover, the prototypes are more consistent and the model is more robust to image perturbations than the state of the art method ProtoPNet. We verify our findings on two datasets, the CUB-200-2011 and the Stanford Cars.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset