A Comprehensive Analysis about Unsupervised Outlier Detection for Images

Unsupervised outlier detection that automatically identifies whether visual systems involve anomalous images is a significant research topic. However, most approaches are limited to natural images because they rely on frozen and pre-trained feature extractors. So that their performance cannot be maintained in practical scenarios, especially for industrial inspection and medical imaging. In this work, we first revisit this task and then introduce a versatile unsupervised outlier detection framework to enrich the application domains. The core idea of this framework is to improve feature discriminativess via exploiting intrinsic distribution priors. Evaluated on 3 domains and 14 benchmark datasets, our proposed solution achieves state-of-the-art performance and significantly outperforms existing methods. More importantly, we show its plug-andplay property that can be integrated into diverse visual applications to improve their robustness, such as image classification and 3D reconstruction. Our code is available at https://github.com/zhliu-uod/VUOD.