English

Trust, but Verify: Using Self-Supervised Probing to Improve Trustworthiness

Machine Learning 2023-02-07 v1 Artificial Intelligence

Abstract

Trustworthy machine learning is of primary importance to the practical deployment of deep learning models. While state-of-the-art models achieve astonishingly good performance in terms of accuracy, recent literature reveals that their predictive confidence scores unfortunately cannot be trusted: e.g., they are often overconfident when wrong predictions are made, or so even for obvious outliers. In this paper, we introduce a new approach of self-supervised probing, which enables us to check and mitigate the overconfidence issue for a trained model, thereby improving its trustworthiness. We provide a simple yet effective framework, which can be flexibly applied to existing trustworthiness-related methods in a plug-and-play manner. Extensive experiments on three trustworthiness-related tasks (misclassification detection, calibration and out-of-distribution detection) across various benchmarks verify the effectiveness of our proposed probing framework.

Keywords

Cite

@article{arxiv.2302.02628,
  title  = {Trust, but Verify: Using Self-Supervised Probing to Improve Trustworthiness},
  author = {Ailin Deng and Shen Li and Miao Xiong and Zhirui Chen and Bryan Hooi},
  journal= {arXiv preprint arXiv:2302.02628},
  year   = {2023}
}

Comments

European Conference on Computer Vision 2022

R2 v1 2026-06-28T08:32:44.702Z