Omni-frequency Channel-selection Representations for Unsupervised Anomaly Detection

Abstract

Density-based and classification-based methods have ruled unsupervised anomaly detection in recent years, while reconstruction-based methods are rarely mentioned for the poor reconstruction ability and low performance. However, the latter requires no costly extra training samples for the unsupervised training that is more practical, so this paper focuses on improving this kind of method and proposes a novel Omni-frequency Channel-selection Reconstruction (OCR-GAN) network to handle anomaly detection task in a perspective of frequency. Concretely, we propose a Frequency Decoupling (FD) module to decouple the input image into different frequency components and model the reconstruction process as a combination of parallel omni-frequency image restorations, as we observe a significant difference in the frequency distribution of normal and abnormal images. Given the correlation among multiple frequencies, we further propose a Channel Selection (CS) module that performs frequency interaction among different encoders by adaptively selecting different channels. Abundant experiments demonstrate the effectiveness and superiority of our approach over different kinds of methods, e.g., achieving a new state-of-the-art 98.3 detection AUC on the MVTec AD dataset without extra training data that markedly surpasses the reconstruction-based baseline by +38.1 and the current SOTA method by +0.3. Source code is available at https://github.com/zhangzjn/OCR-GAN.

References in corpus (14)

• Adam: A Method for Stochastic Optimization
• Auto-Encoding Variational Bayes
• Improved Regularization of Convolutional Neural Networks with Cutout
• Uninformed Students: Student-Teacher Anomaly Detection with Discriminative Latent Embeddings
• Segmentation-Based Deep-Learning Approach for Surface-Defect Detection
• Improving Unsupervised Defect Segmentation by Applying Structural Similarity to Autoencoders
• Deep Anomaly Detection Using Geometric Transformations
• Sub-Image Anomaly Detection with Deep Pyramid Correspondences
• Learning Deep Features for One-Class Classification
• CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instances
• Localizing Anomalies from Weakly-Labeled Videos
• Deep Nearest Neighbor Anomaly Detection
• Reference-based Defect Detection Network
• Discriminative-Generative Representation Learning for One-Class Anomaly Detection

Cited by in corpus (11)

• A Survey on Unsupervised Anomaly Detection Algorithms for Industrial Images
• Segment Any Anomaly without Training via Hybrid Prompt Regularization
• VarAD: Lightweight High-Resolution Image Anomaly Detection via Visual Autoregressive Modeling
• Distillation-based fabric anomaly detection
• SoftPatch+: Fully Unsupervised Anomaly Classification and Segmentation
• 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
• Foundation Models and Transformers for Anomaly Detection: A Survey
• Dual-path Frequency Discriminators for Few-shot Anomaly Detection
• Triad: Empowering LMM-based Anomaly Detection with Vision Expert-guided Visual Tokenizer and Manufacturing Process
• Contrastive Knowledge Distillation for Anomaly Detection in Multi-Illumination/Focus Display Images