Confidence Scoring Using Whitebox Meta-models with Linear Classifier Probes

Tongfei Chen, Jirí Navrátil, Vijay S. Iyengar, Karthikeyan Shanmugam

Abstract: We propose a novel confidence scoring mechanism for deep neural networks based on a two-model paradigm involving a base model and a meta-model. The confidence score is learned by the meta-model obs...