arxivcs.CV2026-06-25
Beyond Points: Spherical Distributional Part Prototypes for Interpretable Classification
Duarte Leão, Diogo Pereira Araújo, Catarina Barata, Carlos Santiago
Prototype-based neural networks aim to provide intrinsic interpretability by grounding predictions in a small set of part prototypes. However, modern vision backbones typically operate in normalized, directional embedding spaces where each semantic part exhibits substantial intra…