AI RESEARCH
Target-Agnostic Calibration under Distribution Shift with Frequency-Aware Gradient Rectification
arXiv CS.AI
•
ArXi:2508.19830v2 Announce Type: replace-cross Real-world model deployments inevitably encounter distribution shifts, rendering the confidence estimates of deep neural networks highly unreliable, posing severe risks in safety-critical applications. Existing methods improve calibration via