ProtoS-ViT: Visual foundation models for sparse self-explainable classifications

Prototypical networks aim to build intrinsically explainable models based on the linear summation of concepts. However, important challenges remain in the transparency, compactness, and meaningfulness of the explanations provided by these models. This work demonstrates how frozen pre-trained ViT backbones can be effectively turned into prototypical models for both general and domain-specific tasks, in our case biomedical image classifiers. By leveraging strong spatial features combined with a novel prototypical head, ProtoS-ViT surpasses existing prototypical models showing strong performance in terms of accuracy, compactness, and explainability. Model explainability is evaluated through an extensive set of quantitative and qualitative metrics which serve as a general benchmark for the development of prototypical models. Code is available at https://github.com/hturbe/protosvit.