English

Evaluating Uncertainty Calibration for Open-Set Recognition

Computer Vision and Pattern Recognition 2022-05-17 v1 Robotics

Abstract

Despite achieving enormous success in predictive accuracy for visual classification problems, deep neural networks (DNNs) suffer from providing overconfident probabilities on out-of-distribution (OOD) data. Yet, accurate uncertainty estimation is crucial for safe and reliable robot autonomy. In this paper, we evaluate popular calibration techniques for open-set conditions in a way that is distinctly different from the conventional evaluation of calibration methods on OOD data. Our results show that closed-set DNN calibration approaches are much less effective for open-set recognition, which highlights the need to develop new DNN calibration methods to address this problem.

Keywords

Cite

@article{arxiv.2205.07160,
  title  = {Evaluating Uncertainty Calibration for Open-Set Recognition},
  author = {Zongyao Lyu and Nolan B. Gutierrez and William J. Beksi},
  journal= {arXiv preprint arXiv:2205.07160},
  year   = {2022}
}

Comments

To be presented at the 2022 IEEE International Conference on Robotics and Automation (ICRA) Workshop on Safe and Reliable Robot Autonomy under Uncertainty

R2 v1 2026-06-24T11:17:32.274Z