Exploring the Optimization Objective of One-Class Classification for Anomaly Detection

TL;DR

This paper investigates the optimization objectives in one-class classification for anomaly detection, revealing that alternative norm-based spaces can replace traditional hypersphere centers, leading to a simple, effective, data-agnostic method with state-of-the-art results.

Contribution

It introduces a theoretical analysis showing the equivalence of various norm-based spaces as optimization objectives in OCC, and proposes a novel, simple, data-agnostic OCC method leveraging this insight.

Findings

Achieved state-of-the-art performance in anomaly detection tasks.

Validated the theoretical equivalence of norm-based optimization spaces.

Demonstrated the effectiveness of a minimalistic 1x1 convolutional layer approach.

Abstract

One-class classification (OCC) is a longstanding method for anomaly detection. With the powerful representation capability of the pre-trained backbone, OCC methods have witnessed significant performance improvements. Typically, most of these OCC methods employ transfer learning to enhance the discriminative nature of the pre-trained backbone's features, thus achieving remarkable efficacy. While most current approaches emphasize feature transfer strategies, we argue that the optimization objective space within OCC methods could also be an underlying critical factor influencing performance. In this work, we conducted a thorough investigation into the optimization objective of OCC. Through rigorous theoretical analysis and derivation, we unveil a key insights: any space with the suitable norm can serve as an equivalent substitute for the hypersphere center, without relying on the distribution assumption of training samples. Further, we provide guidelines for determining the feasible domain of norms for the OCC optimization objective. This novel insight sparks a simple and data-agnostic deep one-class classification method. Our method is straightforward, with a single 1x1 convolutional layer as a trainable projector and any space with suitable norm as the optimization objective. Extensive experiments validate the reliability and efficacy of our findings and the corresponding methodology, resulting in state-of-the-art performance in both one-class classification and industrial vision anomaly detection and segmentation tasks.