Decision Fusion Network with Perception Fine-tuning for Defect Classification

TL;DR

This paper introduces DFNet, a novel deep learning framework that combines semantic and feature decision fusion with perception fine-tuning to improve surface defect classification accuracy in challenging industrial inspection scenarios.

Contribution

The paper proposes a decision fusion network with a new module and fine-tuning strategy to enhance defect classification, especially under low-contrast and complex background conditions.

Findings

Achieved 96.1% AP on KolektorSDD2 dataset.

Achieved 94.6% mAP on Magnetic-tile-defect dataset.

Demonstrated improved robustness over existing methods.

Abstract

Surface defect inspection is an important task in industrial inspection. Deep learning-based methods have demonstrated promising performance in this domain. Nevertheless, these methods still suffer from misjudgment when encountering challenges such as low-contrast defects and complex backgrounds. To overcome these issues, we present a decision fusion network (DFNet) that incorporates the semantic decision with the feature decision to strengthen the decision ability of the network. In particular, we introduce a decision fusion module (DFM) that extracts a semantic vector from the semantic decision branch and a feature vector for the feature decision branch and fuses them to make the final classification decision. In addition, we propose a perception fine-tuning module (PFM) that fine-tunes the foreground and background during the segmentation stage. PFM generates the semantic and feature outputs that are sent to the classification decision stage. Furthermore, we present an inner-outer separation weight matrix to address the impact of label edge uncertainty during segmentation supervision. Our experimental results on the publicly available datasets including KolektorSDD2 (96.1% AP) and Magnetic-tile-defect-datasets (94.6% mAP) demonstrate the effectiveness of the proposed method.