Rethinking Unsupervised Outlier Detection via Multiple Thresholding

TL;DR

This paper introduces a multiple thresholding module for unsupervised image outlier detection, improving scoring methods by better separating inliers and outliers, and enhancing feature representation without labeled data.

Contribution

The proposed Multi-T module enables effective thresholding and self-supervision in unsupervised outlier detection, leading to significant performance improvements.

Findings

Multi-T improves existing outlier scoring methods.

Multi-T achieves state-of-the-art results with a simple distance-based method.

Extensive experiments validate the effectiveness of Multi-T.

Abstract

In the realm of unsupervised image outlier detection, assigning outlier scores holds greater significance than its subsequent task: thresholding for predicting labels. This is because determining the optimal threshold on non-separable outlier score functions is an ill-posed problem. However, the lack of predicted labels not only hiders some real applications of current outlier detectors but also causes these methods not to be enhanced by leveraging the dataset's self-supervision. To advance existing scoring methods, we propose a multiple thresholding (Multi-T) module. It generates two thresholds that isolate inliers and outliers from the unlabelled target dataset, whereas outliers are employed to obtain better feature representation while inliers provide an uncontaminated manifold. Extensive experiments verify that Multi-T can significantly improve proposed outlier scoring methods. Moreover, Multi-T contributes to a naive distance-based method being state-of-the-art.