Unsupervised Two-Stage Anomaly Detection
arXiv:2103.11671
Abstract
Anomaly detection from a single image is challenging since anomaly data is always rare and can be with highly unpredictable types. With only anomaly-free data available, most existing methods train an AutoEncoder to reconstruct the input image and find the difference between the input and output to identify the anomalous region. However, such methods face a potential problem - a coarse reconstruction generates extra image differences while a high-fidelity one may draw in the anomaly. In this paper, we solve this contradiction by proposing a two-stage approach, which generates high-fidelity yet anomaly-free reconstructions. Our Unsupervised Two-stage Anomaly Detection (UTAD) relies on two technical components, namely the Impression Extractor (IE-Net) and the Expert-Net. The IE-Net and Expert-Net accomplish the two-stage anomaly-free image reconstruction task while they also generate intuitive intermediate results, making the whole UTAD interpretable. Extensive experiments show that our method outperforms state-of-the-arts on four anomaly detection datasets with different types of real-world objects and textures.
References in corpus (15)
- Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
- Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
- Progressive Growing of GANs for Improved Quality, Stability, and Variation
- Uninformed Students: Student-Teacher Anomaly Detection with Discriminative Latent Embeddings
- Learning Representations by Maximizing Mutual Information Across Views
- Improving Unsupervised Defect Segmentation by Applying Structural Similarity to Autoencoders
- Mutual Mean-Teaching: Pseudo Label Refinery for Unsupervised Domain Adaptation on Person Re-identification
- Multimodal Unsupervised Image-to-Image Translation
- On Mutual Information Maximization for Representation Learning
- OCGAN: One-class Novelty Detection Using GANs with Constrained Latent Representations
- Weakly Supervised Action Localization by Sparse Temporal Pooling Network
- Unsupervised Learning of Anomaly Detection from Contaminated Image Data using Simultaneous Encoder Training
- Encoding Structure-Texture Relation with P-Net for Anomaly Detection in Retinal Images
- Towards Visually Explaining Variational Autoencoders
- Latent Space Autoregression for Novelty Detection