Multiscale Adversarial and Weighted Gradient Domain Adaptive Network for Data Scarcity Surface Defect Detection
- 12 July 2021
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 70 (00189456), 1-10
- https://doi.org/10.1109/tim.2021.3096284
Abstract
Surface defect detection is a challenging task in industrial manufacture. Recent methods using supervised learning need a large-scale dataset to achieve precise detection. However, the time-consuming and the difficulty of data acquisition make it difficult to build a large-scale dataset. This article proposes a domain adaptive network, called multiscale adversarial and weighted gradient domain adaptive network (MWDAN) for data scarcity surface defect detection. By MWDAN, the detection model trained from a small-scale dataset can gain the knowledge of transfer from another large-scale dataset, that is to say, even for a training dataset that is difficult to collect huge amounts of data, a good defect detection model can also be constructed, aided by another dataset that is relatively easy to acquire. The MWDAN is constructed in two levels. In the image level, a multiscale domain feature adaptation approach is proposed to solve the domain shift between the source domain and the target domain. In the instance level, a piecewise weighted gradient reversal layer (PWGRL) is designed to balance the weight of the backpropagation gradient for the hard- and easy-confused samples in domain classification and force confusion. Then, the PWGRL can reduce the local instance difference to further promote domain consistency. The experiments on mental surface defect detection show encourage results by the proposed MWDAN method.Keywords
Funding Information
- National Key Research and Development Program of China (2019YFB1312600)
- National Natural Science Foundation of China (52075480)
- Key Research and Development Program of Zhejiang Province (2021C01008)
- Natural Science Foundation of Zhejiang Province (Y19E050078)
This publication has 31 references indexed in Scilit:
- Feature Pyramid Networks for Object DetectionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2017
- Deep Reconstruction-Classification Networks for Unsupervised Domain AdaptationPublished by Springer Science and Business Media LLC ,2016
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksIEEE Transactions on Pattern Analysis and Machine Intelligence, 2016
- Deep Residual Learning for Image RecognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2016
- A noise robust method based on completed local binary patterns for hot-rolled steel strip surface defectsApplied Surface Science, 2013
- Linear Discriminant AnalysisPublished by Springer Science and Business Media LLC ,2013
- Domain Transfer Multiple Kernel LearningIEEE Transactions on Pattern Analysis and Machine Intelligence, 2012
- Histograms of Oriented Gradients for Human DetectionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Least Squares Support Vector Machine ClassifiersNeural Processing Letters, 1999
- Object recognition from local scale-invariant featuresPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1999