CCAD: Compressed Global Feature Conditioned Anomaly Detection

TL;DR

CCAD introduces a novel anomaly detection method that combines global feature conditioning with adaptive compression, improving robustness, efficiency, and outperforming existing methods in industrial anomaly detection tasks.

Contribution

The paper proposes CCAD, a new anomaly detection approach that integrates global features as conditions and employs adaptive compression for better generalization and training speed.

Findings

CCAD outperforms state-of-the-art methods in AUC metrics.

CCAD achieves faster convergence during training.

A new annotated version of DAGM 2007 dataset validates effectiveness.

Abstract

Anomaly detection holds considerable industrial significance, especially in scenarios with limited anomalous data. Currently, reconstruction-based and unsupervised representation-based approaches are the primary focus. However, unsupervised representation-based methods struggle to extract robust features under domain shift, whereas reconstruction-based methods often suffer from low training efficiency and performance degradation due to insufficient constraints. To address these challenges, we propose a novel method named Compressed Global Feature Conditioned Anomaly Detection (CCAD). CCAD synergizes the strengths of both paradigms by adapting global features as a new modality condition for the reconstruction model. Furthermore, we design an adaptive compression mechanism to enhance both generalization and training efficiency. Extensive experiments demonstrate that CCAD consistently outperforms state-of-the-art methods in terms of AUC while achieving faster convergence. In addition, we contribute a reorganized and re-annotated version of the DAGM 2007 dataset with new annotations to further validate our method's effectiveness. The code for reproducing main results is available at https://github.com/chloeqxq/CCAD.