Interpretable Image Classification with Differentiable Prototypes Assignment
It addresses interpretability in image classification for domains like fine-grained recognition, offering a more efficient and accurate method compared to existing approaches.
The paper tackles the problem of interpretable image classification by introducing ProtoPool, a model that uses a shared pool of prototypes with differentiable assignment, eliminating the need for pruning and achieving state-of-the-art accuracy on CUB-200-2011 and Stanford Cars datasets while reducing prototype count.
We introduce ProtoPool, an interpretable image classification model with a pool of prototypes shared by the classes. The training is more straightforward than in the existing methods because it does not require the pruning stage. It is obtained by introducing a fully differentiable assignment of prototypes to particular classes. Moreover, we introduce a novel focal similarity function to focus the model on the rare foreground features. We show that ProtoPool obtains state-of-the-art accuracy on the CUB-200-2011 and the Stanford Cars datasets, substantially reducing the number of prototypes. We provide a theoretical analysis of the method and a user study to show that our prototypes are more distinctive than those obtained with competitive methods.