CVSep 28, 2021

Y-GAN: Learning Dual Data Representations for Efficient Anomaly Detection

arXiv:2109.14020v23 citations
Originality Incremental advance
AI Analysis

This work addresses anomaly detection for applications like image analysis, but it appears incremental as it builds on existing reconstruction-based methods with novel disentanglement techniques.

The authors tackled the problem of anomaly detection by proposing Y-GAN, a reconstruction-based model that learns dual latent representations to separate semantic and residual information, achieving efficient anomaly detection across multiple datasets like MNIST, FMNIST, CIFAR10, and PlantVillage.

We propose a novel reconstruction-based model for anomaly detection, 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, 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 consistency loss is proposed to prevent information leakage between the latent spaces. The model is trained in a one-class learning setting using normal training data only. Due to the separation of semantically-relevant and residual information, Y-GAN is able to derive informative data representations that allow for efficient 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 datasets, i.e., MNIST, FMNIST and CIFAR10, and PlantVillage.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes