A knowledge distillation-based multi-scale relation-prototypical network for cross-domain few-shot defect classification

Jiaqi Zhao (), Xiaolong Qian (), Yunzhou Zhang, Dexing Shan, Xiaozheng Liu, Sonya Coleman and Dermot Kerr
Additional contact information
Jiaqi Zhao: Northeastern University
Xiaolong Qian: Northeastern University
Yunzhou Zhang: Northeastern University
Dexing Shan: Northeastern University
Xiaozheng Liu: Northeastern University
Sonya Coleman: University of Ulster
Dermot Kerr: University of Ulster

Journal of Intelligent Manufacturing, 2024, vol. 35, issue 2, No 21, 857 pages

Abstract: Abstract Surface defect classification plays a very important role in industrial production and mechanical manufacturing. However, there are currently some challenges hindering its use. The first is the similarity of different defect samples makes classification a difficult task. Second, the lack of defect samples leads to poor accuracies when using deep learning methods. In this paper, we first design a novel backbone network, ResMSNet, which draws on the idea of multi-scale feature extraction for small discriminative regions in defect samples. Then, we introduce few-shot learning for defect classification and propose a Relation-Prototypical network (RPNet), which combines the characteristics of ProtoNet and RelationNet and provides classification by linking the prototypes distances and the nonlinear relation scores. Next, we consider a more realistic scenario where the base dataset for training the model and target defect dataset for applying the model are usually obtained from domains with large differences, called cross-domain few-shot learning. Hence, we further improve RPNet to KD-RPNet inspired by knowledge distillation methods. Through extensive comparative experiments and ablation experiments, we demonstrate that either our ResMSNet or RPNet proves its effectiveness and KD-RPNet outperforms other state-of-the-art approaches for few-shot defect classification.

Keywords: Few-shot learning; Defect classification; Multi-scale feature encoder; Cross-domain; Knowledge distillation (search for similar items in EconPapers)
Date: 2024
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s10845-023-02080-w Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:joinma:v:35:y:2024:i:2:d:10.1007_s10845-023-02080-w

Ordering information: This journal article can be ordered from
http://www.springer.com/journal/10845

DOI: 10.1007/s10845-023-02080-w

Access Statistics for this article

Journal of Intelligent Manufacturing is currently edited by Andrew Kusiak

More articles in Journal of Intelligent Manufacturing from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().