CVPR 2025poster0 citations

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}
}
FlexUOD: The Answer to Real-world Unsupervised Image Outlier Detection · CVPR 2025