Collaborative Discrepancy Optimization for Reliable Image Anomaly Localization

Abstract

Most unsupervised image anomaly localization methods suffer from overgeneralization because of the high generalization abilities of convolutional neural networks, leading to unreliable predictions. To mitigate the overgeneralization, this study proposes to collaboratively optimize normal and abnormal feature distributions with the assistance of synthetic anomalies, namely collaborative discrepancy optimization (CDO). CDO introduces a margin optimization module and an overlap optimization module to optimize the two key factors determining the localization performance, i.e., the margin and the overlap between the discrepancy distributions (DDs) of normal and abnormal samples. With CDO, a large margin and a small overlap between normal and abnormal DDs are obtained, and the prediction reliability is boosted. Experiments on MVTec2D and MVTec3D show that CDO effectively mitigates the overgeneralization and achieves great anomaly localization performance with real-time computation efficiency. A real-world automotive plastic parts inspection application further demonstrates the capability of the proposed CDO. Code is available on https://github.com/caoyunkang/CDO.

arXiv commentAccepted by IEEE Transactions on Industrial Informatics

References in corpus (6)

• Decoupled Weight Decay Regularization
• Uninformed Students: Student-Teacher Anomaly Detection with Discriminative Latent Embeddings
• The MVTec 3D-AD Dataset for Unsupervised 3D Anomaly Detection and Localization
• DFR: Deep Feature Reconstruction for Unsupervised Anomaly Segmentation
• Student-Teacher Feature Pyramid Matching for Anomaly Detection
• Anomaly Detection via Reverse Distillation from One-Class Embedding

Cited by in corpus (8)

• AdaCLIP: Adapting CLIP with Hybrid Learnable Prompts for Zero-Shot Anomaly Detection
• Complementary Pseudo Multimodal Feature for Point Cloud Anomaly Detection
• Segment Any Anomaly without Training via Hybrid Prompt Regularization
• Progressive Boundary Guided Anomaly Synthesis for Industrial Anomaly Detection
• VarAD: Lightweight High-Resolution Image Anomaly Detection via Visual Autoregressive Modeling
• Dual-path Frequency Discriminators for Few-shot Anomaly Detection
• Multi-AD: Cross-Domain Unsupervised Anomaly Detection for Medical and Industrial Applications
• ISP-AD: A Large-Scale Real-World Dataset for Advancing Industrial Anomaly Detection with Synthetic and Real Defects