Fine-grained Anomaly Detection via Multi-task Self-Supervision

TL;DR

This paper introduces a multi-task self-supervised learning approach that significantly improves fine-grained anomaly detection by combining high-scale shape features with low-scale fine features, outperforming existing methods.

Contribution

The paper proposes a novel multi-task framework that integrates shape and fine features for enhanced fine-grained anomaly detection, addressing limitations of previous self-supervised methods.

Findings

Achieves up to 31% relative error reduction in AUROC

Outperforms state-of-the-art methods on various anomaly detection tasks

Demonstrates effectiveness of multi-task self-supervision for fine-grained anomalies

Abstract

Detecting anomalies using deep learning has become a major challenge over the last years, and is becoming increasingly promising in several fields. The introduction of self-supervised learning has greatly helped many methods including anomaly detection where simple geometric transformation recognition tasks are used. However these methods do not perform well on fine-grained problems since they lack finer features. By combining in a multi-task framework high-scale shape features oriented task with low-scale fine features oriented task, our method greatly improves fine-grained anomaly detection. It outperforms state-of-the-art with up to 31% relative error reduction measured with AUROC on various anomaly detection problems.