Home > Research > Publications & Outputs > Dual-Metric Neural Network with Attention Guida...
View graph of relations

Dual-Metric Neural Network with Attention Guidance for Surface Defect Few-Shot Detection in Smart Manufacturing

Research output: Contribution to Journal/MagazineJournal articlepeer-review

E-pub ahead of print
  • Pengjie Gao
  • Junliang Wang
  • Min Xia
  • Zijin Qin
  • Jie Zhang
Close
<mark>Journal publication date</mark>7/09/2023
<mark>Journal</mark>Journal of Manufacturing Science and Engineering
Number of pages31
Pages (from-to)1-31
Publication StatusE-pub ahead of print
Early online date7/09/23
<mark>Original language</mark>English

Abstract

As an important application of human-robot collaboration, intelligent detection of surface defects is crucial for production quality control, which also helps in relieving the workload of technical staff in human-centric smart manufacturing. To accurately detect defects with limited samples in industrial practice, a dual-metric neural network with attention guided is proposed. First, an attention-guided recognition network with channel attention and position attention module is designed to efficiently learn representative defect features with limited samples. Second, aiming to detect defects with confusing surface images, a dual-metric function is presented to learn the classification boundary by controlling the distance of samples in feature space from intra-class and inter-class. The experiment results on the fabric defect dataset demonstrate that the proposed approach outperforms state-of-the-art methods in accuracy, recall, precision, F1-score, and few-shot accuracy. Further comparative experiments reveal that the dual-metric function is superior in improving the few-shot detection accuracy for the defect patterns of fabric.