AI RESEARCH
This Looks Distinctly Like That: Grounding Interpretable Recognition in Stiefel Geometry against Neural Collapse
arXiv CS.CV
•
ArXi:2603.08374v1 Announce Type: new Prototype networks provide an intrinsic case based explanation mechanism, but their interpretability is often undermined by prototype collapse, where multiple prototypes degenerate to highly redundant evidence. We attribute this failure mode to the terminal dynamics of Neural Collapse, where cross entropy optimization suppresses intra class variance and drives class conditional features toward a low dimensional limit.