Combining GANs and AutoEncoders for Efficient Anomaly Detection

TL;DR

This paper introduces CBiGAN, a novel anomaly detection method combining GANs and autoencoders with a consistency constraint, achieving high accuracy and efficiency, especially in texture anomalies, on high-resolution images.

Contribution

The paper presents CBiGAN, a new approach that enhances BiGANs with a regularization term for improved anomaly detection performance and computational efficiency.

Findings

Outperforms standard BiGANs significantly

Achieves comparable results to iterative methods with less computation

Sets new state-of-the-art in texture anomaly detection

Abstract

In this work, we propose CBiGAN -- a novel method for anomaly detection in images, where a consistency constraint is introduced as a regularization term in both the encoder and decoder of a BiGAN. Our model exhibits fairly good modeling power and reconstruction consistency capability. We evaluate the proposed method on MVTec AD -- a real-world benchmark for unsupervised anomaly detection on high-resolution images -- and compare against standard baselines and state-of-the-art approaches. Experiments show that the proposed method improves the performance of BiGAN formulations by a large margin and performs comparably to expensive state-of-the-art iterative methods while reducing the computational cost. We also observe that our model is particularly effective in texture-type anomaly detection, as it sets a new state of the art in this category. Our code is available at https://github.com/fabiocarrara/cbigan-ad/.