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

TL;DR

This paper introduces a novel anomaly detection framework called HetNet, which uses noise fusion and distillation techniques to improve defect detection accuracy in complex industrial environments with varying conditions.

Contribution

The paper presents a new collaborative distillation heterogeneous teacher network (HetNet) with adaptive feature fusion and noise generation modules for robust industrial anomaly detection.

Findings

Achieved approximately 10% improvement on MSC-AD benchmark.

Demonstrated state-of-the-art results on multiple datasets.

Validated effectiveness in real-world industrial environments.

Abstract

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/