Skip to content (access key 's')
Logo of Technion
Logo of CS Department
Logo of CS4People

The Taub Faculty of Computer Science Events and Talks

Large Scale Studies Of Deep Neural Networks For Uncertainty Estimation And Class-out-of-Distribution Detection
event speaker icon
Ido Galil (Ph.D. Thesis Seminar)
event date icon
Wednesday, 10.07.2024, 12:30
event location icon
Zoom Lecture: 92810808120 & Taub 9
event speaker icon
Advisor: Prof. Ran El-Yaniv
In this seminar, I will discuss two of my papers (published in ICLR 2023) on uncertainty estimation and class-out-of-distribution detection. We present a novel framework to benchmark the ability of image classifiers to detect class-out-of-distribution (C-OOD) instances (i.e., instances whose true labels do not appear in the training distribution) at various levels of detection difficulty. We apply this technique to ImageNet, and benchmark 500+ pretrained, publicly available, ImageNet-1k classifiers. We then evaluate these classifiers both for their C-OOD detection performance (second paper) and for their uncertainty estimation performance (first paper), i.e., their ranking, calibration, and selective classification performance. This results in a large-scale study that reveals many factors (such as architecture types and training regimes) previously unknown to contribute to performance.