Noise Fusion-based Distillation Learning for Anomaly Detection in Complex Industrial Environments

Anomaly detection and localization in automated industrial manufacturing can significantly enhance production efficiency and product quality. Existing methods are capable of detecting surface defects in pre-defined or controlled imaging environments. However, accurately detecting workpiece defects in complex and unstructured industrial environments with varying views, poses and illumination remains challenging. We propose a novel anomaly detection and localization method specifically designed to handle inputs with perturbative patterns. Our approach introduces a new framework based on a collaborative distillation heterogeneous teacher network (HetNet), an adaptive local-global feature fusion module, and a local multivariate Gaussian noise generation module. HetNet can learn to model the complex feature distribution of normal patterns using limited information about local disruptive changes. We conducted extensive experiments on mainstream benchmarks. HetNet demonstrates superior performance with approximately 10% improvement across all evaluation metrics on MSC-AD under industrial conditions, while achieving state-of-the-art results on other datasets, validating its resilience to environmental fluctuations and its capability to enhance the reliability of industrial anomaly detection systems across diverse scenarios. Tests in real-world environments further confirm that HetNet can be effectively integrated into production lines to achieve robust and real-time anomaly detection. Codes, images and videos are published on the project website at: https://zihuatanejoyu.github.io/HetNet/

Authors

• Jiawen Yu
• Jieji Ren
• Yang Chang
• Qiaojun Yu
• Xuan Tong
• Boyang Wang 0003
• Yan Song
• You Li
• Xinji Mai
• Wenqiang Zhang

Keywords

• Location awareness
• Production
• Benchmark testing
• Robustness
• Real-time systems
• Product design
• Quality assessment
• Anomaly detection
• Videos
• Resilience
• Industrial Environment
• Environmental Detection
• Complex Industrial Environment
• Complex Environment
• Environmental Control
• Noise Sources
• Normal Pattern
• Industrial Systems
• Feature Fusion
• Collaborative Network
• Adaptive Feature
• Teacher Network
• Complex Defects
• Local Noise
• Feature Fusion Module
• Normal Distribution
• Convolutional Neural Network
• Denoising
• Local Variations
• Multi-scale Features
• Student Network
• Multi-scale Feature Fusion
• Noisy Features
• Hybrid Feature
• Industrial Inspection
• Pre-trained Feature
• Real-world Setting
• Feature Maps
• Encoder-decoder