Learning Trustworthy Model from Noisy Labels based on Rough Set for Surface Defect Detection

TL;DR

This paper introduces a novel framework for surface defect detection that effectively learns from noisy, inconsistent labels by representing suspicious regions precisely, redesigning loss functions, and incorporating a Bayesian module for improved defect identification.

Contribution

The paper proposes a new method that handles noisy labels in surface defect detection without changing network structures or requiring extra labels, using pixel-level representation and a Bayesian module.

Findings

Effective learning from noisy labels demonstrated

Robustness and real-time performance achieved

Improved defect detection accuracy

Abstract

In the surface defect detection, there are some suspicious regions that cannot be uniquely classified as abnormal or normal. The annotating of suspicious regions is easily affected by factors such as workers' emotional fluctuations and judgment standard, resulting in noisy labels, which in turn leads to missing and false detections, and ultimately leads to inconsistent judgments of product quality. Unlike the usual noisy labels, the ones used for surface defect detection appear to be inconsistent rather than mislabeled. The noise occurs in almost every label and is difficult to correct or evaluate. In this paper, we proposed a framework that learns trustworthy models from noisy labels for surface defect defection. At first, to avoid the negative impact of noisy labels on the model, we represent the suspicious regions with consistent and precise elements at the pixel-level and redesign the loss function. Secondly, without changing network structure and adding any extra labels, pluggable spatially correlated Bayesian module is proposed. Finally, the defect discrimination confidence is proposed to measure the uncertainty, with which anomalies can be identified as defects. Our results indicate not only the effectiveness of the proposed method in learning from noisy labels, but also robustness and real-time performance.