Detecting Anomalies using Generative Adversarial Networks on Images

TL;DR

This paper introduces a novel GAN-based approach for anomaly detection in images, leveraging advanced network architectures and training techniques to improve detection accuracy on diverse datasets.

Contribution

It proposes a new GAN model with dense skip connections and self-attention discriminator, enhancing anomaly detection performance in imbalanced datasets.

Findings

Achieves up to 21% improvement on MVTec AD dataset.

Improves detection accuracy by 4.6% on SIXray dataset.

Demonstrates stable training with spectral normalisation.

Abstract

Automatic detection of anomalies such as weapons or threat objects in baggage security, or detecting impaired items in industrial production is an important computer vision task demanding high efficiency and accuracy. Most of the available data in the anomaly detection task is imbalanced as the number of positive/anomalous instances is sparse. Inadequate availability of the data makes training of a deep neural network architecture for anomaly detection challenging. This paper proposes a novel Generative Adversarial Network (GAN) based model for anomaly detection. It uses normal (non-anomalous) images to learn about the normality based on which it detects if an input image contains an anomalous/threat object. The proposed model uses a generator with an encoder-decoder network having dense convolutional skip connections for enhanced reconstruction and to capture the data distribution. A self-attention augmented discriminator is used having the ability to check the consistency of detailed features even in distant portions. We use spectral normalisation to facilitate stable and improved training of the GAN. Experiments are performed on three datasets, viz. CIFAR-10, MVTec AD (for industrial applications) and SIXray (for X-ray baggage security). On the MVTec AD and SIXray datasets, our model achieves an improvement of upto 21% and 4.6%, respectively