Y-GAN: Learning dual data representations for anomaly detection in images

• Published in: Expert systems with applications Vol. 248; p. 123410
• Main Authors: Ivanovska, Marija, Štruc, Vitomir
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 15-08-2024
• Subjects: Anomaly detection; Disentangled data representations; One-class learning; One-class learning; Disentangled data representations; Anomaly detection
• ISSN: 0957-4174; 1873-6793
• DOI: 10.1016/j.eswa.2024.123410

We propose a novel reconstruction-based model for anomaly detection in image data, called ’Y-GAN’. The model consists of a Y-shaped auto-encoder and represents images in two separate latent spaces. The first captures meaningful image semantics, which are key for representing (normal) training data, whereas the second encodes low-level residual image characteristics. To ensure the dual representations encode mutually exclusive information, a disentanglement procedure is designed around a latent (proxy) classifier. Additionally, a novel representation-consistency mechanism is proposed to prevent information leakage between the latent spaces. The model is trained in a one-class learning setting using only normal training data. Due to the separation of semantically-relevant and residual information, Y-GAN is able to derive informative data representations that allow for efficacious anomaly detection across a diverse set of anomaly detection tasks. The model is evaluated in comprehensive experiments with several recent anomaly detection models using four popular image datasets, i.e., MNIST, FMNIST, CIFAR10, and PlantVillage. Experimental results show that Y-GAN outperforms all tested models by a considerable margin and yields state-of-the-art results. The source code for the model is made publicly available at https://github.com/MIvanovska/Y-GAN.
•We propose a novel state-of-the-art approach Y-GAN for anomaly detection in images.•Y-GAN disentangles semantically relevant characteristics from residual information.•Y-GAN is trained in a one-class learning setting.•Our proposed approach shows superior results on multiple widely used benchmarks.