Meta Learning-Driven Iterative Refinement for Robust Anomaly Detection in Industrial Inspection

2025-03-03

AI Summary

To address the degradation of anomaly detection model robustness caused by noisy data in industrial quality inspection, this paper proposes a meta-learning-based iterative refinement framework. Our method innovatively couples Model-Agnostic Meta-Learning (MAML) with an interquartile range (IQR)-based statistical rejection mechanism, enabling dynamic identification and removal of noisy training samples in an unsupervised setting—thereby achieving noise-aware, data-adaptive purification. The framework simultaneously enhances robustness against label noise and sensitivity to out-of-distribution (OOD) defects. Experiments on MVTec and KSDD2 demonstrate that our approach improves AUC by over 12% under noisy conditions; remarkably, it maintains stable OOD detection performance even on clean data. This work significantly advances the generalizability and robustness of unsupervised anomaly detection models in real-world industrial scenarios.

Technology Category

• Data Mining & Knowledge Management: Anomaly/Outlier Detection
• Machine Learning: Adversarial Learning & Robustness
• Computer Vision: Adversarial Attacks & Robustness

Application Category

• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs

Abstract

This study investigates the performance of robust anomaly detection models in industrial inspection, focusing particularly on their ability to handle noisy data. We propose to leverage the adaptation ability of meta learning approaches to identify and reject noisy training data to improve the learning process. In our model, we employ Model Agnostic Meta Learning (MAML) and an iterative refinement process through an Inter-Quartile Range rejection scheme to enhance their adaptability and robustness. This approach significantly improves the models capability to distinguish between normal and defective conditions. Our results of experiments conducted on well known MVTec and KSDD2 datasets demonstrate that the proposed method not only excels in environments with substantial noise but can also contribute in case of a clear training set, isolating those samples that are relatively out of distribution, thus offering significant improvements over traditional models.

Problem

• Improves anomaly detection in noisy industrial data
• Uses meta learning to reject noisy training samples
• Enhances model robustness and adaptability in inspections

Innovation

• Meta learning enhances anomaly detection robustness.
• Iterative refinement rejects noisy training data.
• Model Agnostic Meta Learning improves adaptability.