U-Flow: A U-shaped Normalizing Flow for Anomaly Detection with Unsupervised Threshold

TL;DR

This paper introduces U-Flow, a novel unsupervised anomaly detection method combining a U-shaped normalizing flow with a statistical thresholding approach, achieving state-of-the-art results in image anomaly segmentation.

Contribution

The work presents a new U-shaped normalizing flow architecture for anomaly detection, integrating multi-scale features and a robust a contrario thresholding strategy for unsupervised segmentation.

Findings

Achieves a mean pixel-level AUROC of 98.74% on various datasets.

Ranks first in most MVTec-AD categories for anomaly detection.

Outperforms existing methods in multiple evaluation metrics.

Abstract

In this work we propose a one-class self-supervised method for anomaly segmentation in images that benefits both from a modern machine learning approach and a more classic statistical detection theory. The method consists of four phases. First, features are extracted using a multi-scale image Transformer architecture. Then, these features are fed into a U-shaped Normalizing Flow (NF) that lays the theoretical foundations for the subsequent phases. The third phase computes a pixel-level anomaly map from the NF embedding, and the last phase performs a segmentation based on the a contrario framework. This multiple hypothesis testing strategy permits the derivation of robust unsupervised detection thresholds, which are crucial in real-world applications where an operational point is needed. The segmentation results are evaluated using the Mean Intersection over Union (mIoU) metric, and for assessing the generated anomaly maps we report the area under the Receiver Operating Characteristic curve (AUROC), as well as the Area Under the Per-Region-Overlap curve (AUPRO). Extensive experimentation in various datasets shows that the proposed approach produces state-of-the-art results for all metrics and all datasets, ranking first in most MVTec-AD categories, with a mean pixel-level AUROC of 98.74%. Code and trained models are available at https:// github.com/mtailanian/uflow.