Objave

@article{ESWA2024,

title = {Y-GAN: Learning Dual Data Representations for Anomaly Detection in Images},

author = {Marija Ivanovska and Vitomir Štruc},

url = {https://www.sciencedirect.com/science/article/pii/S0957417424002756

https://lmi.fe.uni-lj.si/wp-content/uploads/2024/02/YGAN_Marija.pdf},

doi = {https://doi.org/10.1016/j.eswa.2024.123410},

year  = {2024},

date = {2024-03-01},

urldate = {2024-03-01},

journal = {Expert Systems with Applications (ESWA)},

volume = {248},

number = {123410},

pages = {1-7},

abstract = {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. },

keywords = {anomaly detection, CNN, deep learning, one-class learning, y-gan},

pubstate = {published},

tppubtype = {article}

}