Projects per year
Abstract
The ability to detect unfamiliar or unexpected images is essential for safe deployment of computer vision systems. In the context of classification the task of detecting images outside of a model's training domain is known as out-of-distribution (OOD) detection. While there has been a growing research interest in developing post-hoc OOD detection methods there has been comparably little discussion around how these methods perform when the underlying classifier is not trained on a clean carefully curated dataset. In this work we take a closer look at 20 state-of-the-art OOD detection methods in the (more realistic) scenario where the labels used to train the underlying classifier are unreliable (e.g. crowd-sourced or web-scraped labels). Extensive experiments across different datasets noise types & levels architectures and checkpointing strategies provide insights into the effect of class label noise on OOD detection and show that poor separation between incorrectly classified ID samples vs. OOD samples is an overlooked yet important limitation of existing methods. Code: https://github.com/glhr/ood-labelnoise
Original language | English |
---|---|
Title of host publication | 2024 Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) |
Number of pages | 11 |
Publisher | IEEE (Institute of Electrical and Electronics Engineers) |
Publication date | 16 Sept 2024 |
Pages | 22626-22636 |
ISBN (Print) | 979-8-3503-5301-3 |
ISBN (Electronic) | 979-8-3503-5300-6 |
DOIs | |
Publication status | Published - 16 Sept 2024 |
Event | 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) - Seattle Convention Center, Seattle, United States Duration: 17 Jun 2024 → 21 Jun 2024 https://cvpr.thecvf.com/Conferences/2024 |
Conference
Conference | 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) |
---|---|
Location | Seattle Convention Center |
Country/Territory | United States |
City | Seattle |
Period | 17/06/2024 → 21/06/2024 |
Internet address |
Keywords
- Image Classification
- aleatoric uncertainty
- benchmark
- computer vision
- data uncertainty
- label noise
- noisy labels
- open-set recognition
- out-of-distribution detection
- post-hoc
- Out-of-distribution detection
- Noisy labels
- Image classification
Fingerprint
Dive into the research topics of 'A Noisy Elephant in the Room: Is Your out-of-Distribution Detector Robust to Label Noise?'. Together they form a unique fingerprint.Projects
- 1 Active
-
"Are you sure?" Towards trustworthy computer vision
Humblot-Renaux, G. (PI), Guerrero, S. E. (Supervisor) & Moeslund, T. B. (Supervisor)
01/10/2022 → 01/10/2025
Project: PhD Project