An Overview of Prototype Formulations for Interpretable Deep Learning
This work is incremental, offering a review of existing prototype methods for interpretable deep learning.
The paper provides a comprehensive overview of various prototype formulations for interpretable deep learning, addressing limitations of Euclidean prototypes, and demonstrates their effectiveness on datasets like CUB-200-2011, Stanford Cars, and Oxford Flowers.
Prototypical part networks offer interpretable alternatives to black-box deep learning models. However, many of these networks rely on Euclidean prototypes, which may limit their flexibility. This work provides a comprehensive overview of various prototype formulations. Experiments conducted on the CUB-200-2011, Stanford Cars, and Oxford Flowers datasets demonstrate the effectiveness and versatility of these different formulations.