Deep Learning for Unsupervised Anomaly Localization in Industrial Images: A Survey

Abstract

Currently, deep learning-based visual inspection has been highly successful with the help of supervised learning methods. However, in real industrial scenarios, the scarcity of defect samples, the cost of annotation, and the lack of a priori knowledge of defects may render supervised-based methods ineffective. In recent years, unsupervised anomaly localization algorithms have become more widely used in industrial inspection tasks. This paper aims to help researchers in this field by comprehensively surveying recent achievements in unsupervised anomaly localization in industrial images using deep learning. The survey reviews more than 120 significant publications covering different aspects of anomaly localization, mainly covering various concepts, challenges, taxonomies, benchmark datasets, and quantitative performance comparisons of the methods reviewed. In reviewing the achievements to date, this paper provides detailed predictions and analysis of several future research directions. This review provides detailed technical information for researchers interested in industrial anomaly localization and who wish to apply it to the localization of anomalies in other fields.

arXiv commentsubmit to IEEE TIM

References in corpus (31)

• Representation Learning with Contrastive Predictive Coding
• Deep Learning for Anomaly Detection: A Review
• Deep Learning for Anomaly Detection: A Survey
• Uninformed Students: Student-Teacher Anomaly Detection with Discriminative Latent Embeddings
• A Unifying Review of Deep and Shallow Anomaly Detection
• Segmentation-Based Deep-Learning Approach for Surface-Defect Detection
• Improving Unsupervised Defect Segmentation by Applying Structural Similarity to Autoencoders
• Deep Autoencoding Models for Unsupervised Anomaly Segmentation in Brain MR Images
• Mixed supervision for surface-defect detection: from weakly to fully supervised learning
• Sub-Image Anomaly Detection with Deep Pyramid Correspondences
• FastFlow: Unsupervised Anomaly Detection and Localization via 2D Normalizing Flows
• The MVTec 3D-AD Dataset for Unsupervised 3D Anomaly Detection and Localization
• DFR: Deep Feature Reconstruction for Unsupervised Anomaly Segmentation
• Explainable Deep One-Class Classification
• Anomaly Detection in Medical Imaging -- A Mini Review
• Image Anomalies: a Review and Synthesis of Detection Methods
• Natural Synthetic Anomalies for Self-Supervised Anomaly Detection and Localization
• AnoSeg: Anomaly Segmentation Network Using Self-Supervised Learning
• Anomaly detection and automatic labeling for solar cell quality inspection based on Generative Adversarial Network
• Semi-orthogonal Embedding for Efficient Unsupervised Anomaly Segmentation
• Anomaly localization by modeling perceptual features
• Image/Video Deep Anomaly Detection: A Survey
• A Case for the Score: Identifying Image Anomalies using Variational Autoencoder Gradients
• Unsupervised Two-Stage Anomaly Detection
• Transfer Learning Gaussian Anomaly Detection by Fine-tuning Representations
• Contrastive Predictive Coding for Anomaly Detection
• Railway Anomaly detection model using synthetic defect images generated by CycleGAN
• MLF-SC: Incorporating multi-layer features to sparse coding for anomaly detection
• Improving unsupervised anomaly localization by applying multi-scale memories to autoencoders
• Anomaly Detection By Autoencoder Based On Weighted Frequency Domain Loss
• Anomaly Clustering: Grouping Images into Coherent Clusters of Anomaly Types

Cited by in corpus (6)

• Deep Industrial Image Anomaly Detection: A Survey
• REB: Reducing Biases in Representation for Industrial 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
• Incomplete Multimodal Industrial Anomaly Detection via Cross-Modal Distillation
• Quantum Patch-Based Autoencoder for Anomaly Segmentation