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 multiple 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

Text

Chen et al. "Confidence Scoring Using Whitebox Meta-Models with Linear Classifier Probes." Artificial Intelligence and Statistics, 2019.

Markdown

[Chen et al. "Confidence Scoring Using Whitebox Meta-Models with Linear Classifier Probes." Artificial Intelligence and Statistics, 2019.](https://mlanthology.org/aistats/2019/chen2019aistats-confidence/)

BibTeX

@inproceedings{chen2019aistats-confidence,
  title     = {{Confidence Scoring Using Whitebox Meta-Models with Linear Classifier Probes}},
  author    = {Chen, Tongfei and Navratil, Jiri and Iyengar, Vijay and Shanmugam, Karthikeyan},
  booktitle = {Artificial Intelligence and Statistics},
  year      = {2019},
  pages     = {1467-1475},
  volume    = {89},
  url       = {https://mlanthology.org/aistats/2019/chen2019aistats-confidence/}
}