DFR: Deep Feature Reconstruction for Unsupervised Anomaly Segmentation

Abstract

Automatic detecting anomalous regions in images of objects or textures without priors of the anomalies is challenging, especially when the anomalies appear in very small areas of the images, making difficult-to-detect visual variations, such as defects on manufacturing products. This paper proposes an effective unsupervised anomaly segmentation approach that can detect and segment out the anomalies in small and confined regions of images. Concretely, we develop a multi-scale regional feature generator that can generate multiple spatial context-aware representations from pre-trained deep convolutional networks for every subregion of an image. The regional representations not only describe the local characteristics of corresponding regions but also encode their multiple spatial context information, making them discriminative and very beneficial for anomaly detection. Leveraging these descriptive regional features, we then design a deep yet efficient convolutional autoencoder and detect anomalous regions within images via fast feature reconstruction. Our method is simple yet effective and efficient. It advances the state-of-the-art performances on several benchmark datasets and shows great potential for real applications.

References in corpus (6)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Uninformed Students: Student-Teacher Anomaly Detection with Discriminative Latent Embeddings
• Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discovery
• Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detection
• OCGAN: One-class Novelty Detection Using GANs with Constrained Latent Representations

Cited by in corpus (9)

• Deep Learning for Unsupervised Anomaly Localization in Industrial Images: A Survey
• Collaborative Discrepancy Optimization for Reliable Image Anomaly Localization
• Self-Supervised Anomaly Detection in Computer Vision and Beyond: A Survey and Outlook
• DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detection
• FAIR: Frequency-aware Image Restoration for Industrial Visual Anomaly Detection
• Reconstruction from edge image combined with color and gradient difference for industrial surface anomaly detection
• Unsupervised Anomaly Localization with Structural Feature-Autoencoders
• GRD-Net: Generative-Reconstructive-Discriminative Anomaly Detection with Region of Interest Attention Module
• Constrained unsupervised anomaly segmentation