MLG-STPM: Meta-Learning Guided STPM for Robust Industrial Anomaly Detection Under Label Noise

TL;DR

This paper introduces MLG-STPM, a new method for industrial image anomaly detection that improves performance when training data have noisy labels.

Contribution

MLG-STPM enhances STPM by using a meta-learning inspired guidance mechanism with an Evolving Meta-Set to reduce label noise impact.

Findings

MLG-STPM outperforms STPM in anomaly detection under synthetic label noise up to 20%.

The method achieves competitive results against other approaches on MVTec AD and VisA datasets.

The Evolving Meta-Set helps maintain high-confidence samples without needing clean data.

Abstract

Industrial image anomaly detection (IAD) is crucial for quality control, but its performance often degrades when training data contain label noise. To circumvent the reliance on potentially flawed labels, unsupervised methods that learn from the data distribution itself have become a mainstream approach. Among various unsupervised techniques, student–teacher frameworks have emerged as a highly effective paradigm. Student–Teacher Feature Pyramid Matching (STPM) is a powerful method within this paradigm, yet it is susceptible to such noise. Inspired by STPM and aiming to solve this issue, this paper introduces Meta-Learning Guided STPM (MLG-STPM), a novel framework that enhances STPM’s robustness by incorporating a guidance mechanism inspired by meta-learning. This guidance is achieved through an Evolving Meta-Set (EMS), which dynamically maintains a small high-confidence subset of training samples identified by their low disagreement between student and teacher networks. By training the student network on a combination of the current batch and the EMS, MLG-STPM effectively mitigates the impact of noisy labels without requiring an external clean dataset or complex re-weighting schemes. Comprehensive experiments on the MVTec AD and VisA benchmark datasets with synthetic label noise (0% to 20%) demonstrate that MLG-STPM significantly improves anomaly detection and localization performance compared to the original STPM, especially under higher noise conditions, and achieves competitive results against other relevant approaches.

Figures