AI RESEARCH
ProtoTTA: Prototype-Guided Test-Time Adaptation
arXiv CS.LG
•
ArXi:2604.15494v1 Announce Type: new Deep networks that rely on prototypes-interpretable representations that can be related to the model input-have gained significant attention for balancing high accuracy with inherent interpretability, which makes them suitable for critical domains such as healthcare. However, these models are limited by their reliance on