FaNet: Feature-aware network for few shot classification of strip steel surface defects
Authors:
- Wenli ZhaoWZWenli Zhao
- Kechen SongKSKechen Song
- Yanyan WangYWYanyan Wang
- Shubo LiangSLShubo Liang
- Yunhui YanYYYunhui Yan
- 10 January 2023
- journal article
- research article
- Published by Elsevier in Measurement
- Vol. 208
Abstract
No abstract availableKeywords
Funding Information
- Fundamental Research Funds for the Central Universities (2022JH6/100100023, N2103011)
- Higher Education Discipline Innovation Project (B16009)
- National Natural Science Foundation of China (51805078)
This publication has 28 references indexed in Scilit:
- Defect detection of hot rolled steels with a new object detection framework called classification priority networkComputers & Industrial Engineering, 2019
- Automatic Metallic Surface Defect Detection and Recognition with Convolutional Neural NetworksApplied Sciences, 2018
- Multi-class classification method for strip steel surface defects based on support vector machine with adjustable hyper-sphereJournal of Iron and Steel Research International, 2018
- Learning to Compare: Relation Network for Few-Shot Learning2018
- Multi-class classification method using twin support vector machines with multi-information for steel surface defectsChemometrics and Intelligent Laboratory Systems, 2018
- SphereFace: Deep Hypersphere Embedding for Face Recognition2017
- Deep Residual Learning for Image Recognition2016
- Wide Residual Networks2016
- A noise robust method based on completed local binary patterns for hot-rolled steel strip surface defectsApplied Surface Science, 2013
- A vision inspection system for the surface defects of strongly reflected metal based on multi-class SVMExpert Systems with Applications, 2011