A Hierarchical Transformation-Discriminating Generative Model for Few Shot Anomaly Detection

TL;DR

This paper introduces a hierarchical generative model for few-shot image anomaly detection that leverages multi-scale patch distributions, image transformations, and scale-specific discriminators to effectively identify anomalies with limited training data.

Contribution

The work presents a novel hierarchical transformation-discriminating generative model tailored for few-shot anomaly detection, improving detection accuracy with minimal training samples.

Findings

Outperforms recent baselines on multiple datasets.

Effective in one-shot and few-shot anomaly detection scenarios.

Demonstrates robustness across diverse image datasets.

Abstract

Anomaly detection, the task of identifying unusual samples in data, often relies on a large set of training samples. In this work, we consider the setting of few-shot anomaly detection in images, where only a few images are given at training. We devise a hierarchical generative model that captures the multi-scale patch distribution of each training image. We further enhance the representation of our model by using image transformations and optimize scale-specific patch-discriminators to distinguish between real and fake patches of the image, as well as between different transformations applied to those patches. The anomaly score is obtained by aggregating the patch-based votes of the correct transformation across scales and image regions. We demonstrate the superiority of our method on both the one-shot and few-shot settings, on the datasets of Paris, CIFAR10, MNIST and FashionMNIST as well as in the setting of defect detection on MVTec. In all cases, our method outperforms the recent baseline methods.