Discriminative Feature Learning Framework with Gradient Preference for Anomaly Detection

TL;DR

This paper introduces a novel unsupervised discriminative feature learning framework with gradient preference that enhances anomaly detection and localization, outperforming state-of-the-art methods especially in few-shot scenarios.

Contribution

It proposes a gradient preference-based feature selector and a center-constrained discriminative learning approach to improve anomaly detection and localization performance.

Findings

Achieves competitive results on industrial and medical datasets.

Outperforms state-of-the-art in few-shot anomaly detection.

Enhances inference efficiency through feature repository construction.

Abstract

Unsupervised representation learning has been extensively employed in anomaly detection, achieving impressive performance. Extracting valuable feature vectors that can remarkably improve the performance of anomaly detection are essential in unsupervised representation learning. To this end, we propose a novel discriminative feature learning framework with gradient preference for anomaly detection. Specifically, we firstly design a gradient preference based selector to store powerful feature points in space and then construct a feature repository, which alleviate the interference of redundant feature vectors and improve inference efficiency. To overcome the looseness of feature vectors, secondly, we present a discriminative feature learning with center constrain to map the feature repository to a compact subspace, so that the anomalous samples are more distinguishable from the normal ones. Moreover, our method can be easily extended to anomaly localization. Extensive experiments on popular industrial and medical anomaly detection datasets demonstrate our proposed framework can achieve competitive results in both anomaly detection and localization. More important, our method outperforms the state-of-the-art in few shot anomaly detection.