Confidence Scoring Using Whitebox Meta-models with Linear Classifier Probes
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 observing the base model succeeding/failing at its task. As features to the meta-model, we investigate linear classifier probes inserted between the various layers of the base model. Our experiments demonstrate that this approach outperforms various baselines in a filtering task, i.e., task of rejecting samples with low confidence. Experimental results are presented using CIFAR-10 and CIFAR-100 dataset with and without added noise. We discuss the importance of confidence scoring to bridge the gap between experimental and real-world applications.
Cite
@article{arxiv.1805.05396,
title = {Confidence Scoring Using Whitebox Meta-models with Linear Classifier Probes},
author = {Tongfei Chen and Jiří Navrátil and Vijay Iyengar and Karthikeyan Shanmugam},
journal= {arXiv preprint arXiv:1805.05396},
year = {2019}
}
Comments
Accepted at AISTATS 2019