FlexUOD: The Answer to Real-world Unsupervised Image Outlier Detection
Zhonghang Liu, Kun Zhou, Changshuo Wang, Wen-Yan Lin, Jiangbo Lu
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.
BibTeX
@InProceedings{Liu_2025_CVPR,
author = {Liu, Zhonghang and Zhou, Kun and Wang, Changshuo and Lin, Wen-Yan and Lu, Jiangbo},
title = {FlexUOD: The Answer to Real-world Unsupervised Image Outlier Detection},
booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR)},
month = {June},
year = {2025},
pages = {15183-15193}
}