Back to Search
Start Over
Class-wise Thresholding for Robust Out-of-Distribution Detection
- Source :
- Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2022, pp. 2837-2846
- Publication Year :
- 2021
-
Abstract
- We consider the problem of detecting OoD(Out-of-Distribution) input data when using deep neural networks, and we propose a simple yet effective way to improve the robustness of several popular OoD detection methods against label shift. Our work is motivated by the observation that most existing OoD detection algorithms consider all training/test data as a whole, regardless of which class entry each input activates (inter-class differences). Through extensive experimentation, we have found that such practice leads to a detector whose performance is sensitive and vulnerable to label shift. To address this issue, we propose a class-wise thresholding scheme that can apply to most existing OoD detection algorithms and can maintain similar OoD detection performance even in the presence of label shift in the test distribution.<br />Comment: 12 pages, 7 figures, 7 tables
- Subjects :
- Computer Science - Machine Learning
Computer Science - Artificial Intelligence
Subjects
Details
- Database :
- arXiv
- Journal :
- Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2022, pp. 2837-2846
- Publication Type :
- Report
- Accession number :
- edsarx.2110.15292
- Document Type :
- Working Paper