AI RESEARCH
Margin and Consistency Supervision for Calibrated and Robust Vision Models
arXiv CS.AI
•
ArXi:2603.05812v1 Announce Type: cross Deep vision classifiers often achieve high accuracy while remaining poorly calibrated and fragile under small distribution shifts. We present Margin and Consistency Supervision (MaCS), a simple, architecture-agnostic regularization framework that jointly enforces logit-space separation and local prediction stability.