FlexUOD: The Answer to Real-World Unsupervised Image Outlier Detection
Abstract
How many outliers are within an unlabeled and contaminated dataset? Despite a series of unsupervised outlier detection (UOD) approaches have been proposed, they cannot correctly answer this critical question, resulting in their performance instability across various real-world (varying contamination factor) scenarios. To address this problem, we propose FlexUOD, with a novel contamination factor estimation perspective. FlexUOD not only achieves its remarkable robustness but also is a general and plug-and-play framework, which can significantly improve the performance of existing UOD methods. Extensive experiments demonstrate that FlexUOD achieves state-of-the-art results as well as high efficacy on diverse evaluation benchmarks.
Cite
Text
Liu et al. "FlexUOD: The Answer to Real-World Unsupervised Image Outlier Detection." Conference on Computer Vision and Pattern Recognition, 2025. doi:10.1109/CVPR52734.2025.01414Markdown
[Liu et al. "FlexUOD: The Answer to Real-World Unsupervised Image Outlier Detection." Conference on Computer Vision and Pattern Recognition, 2025.](https://mlanthology.org/cvpr/2025/liu2025cvpr-flexuod/) doi:10.1109/CVPR52734.2025.01414BibTeX
@inproceedings{liu2025cvpr-flexuod,
title = {{FlexUOD: The Answer to Real-World Unsupervised Image Outlier Detection}},
author = {Liu, Zhonghang and Zhou, Kun and Wang, Changshuo and Lin, Wen-Yan and Lu, Jiangbo},
booktitle = {Conference on Computer Vision and Pattern Recognition},
year = {2025},
pages = {15183-15193},
doi = {10.1109/CVPR52734.2025.01414},
url = {https://mlanthology.org/cvpr/2025/liu2025cvpr-flexuod/}
}