Perturbed Progressive Learning for Semisupervised Defect Segmentation
- 24 October 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 35 (5) , 6118-6132
Abstract
Recently, with the development of intelligent manufacturing, the demand for surface defect inspection has been increasing. Deep learning has achieved promising results in defect inspection. However, due to the rareness of defect data and the difficulties of pixelwise annotation, the existing supervised defect inspection methods are too inferior to be implemented in practice. To solve the problem of defect segmentation with few labeled data, we propose a simple and efficient method for semisupervised defect segmentation (SSDS), named perturbed progressive learning (PPL). On the one hand, PPL decouples the predictions of student and teacher networks as well as alleviates overfitting on noisy pseudo-labels. On the other hand, PPL encourages consistency across various perturbations in a broader stagewise scope, alleviating drift caused by the noisy pseudo-labels. Specifically, PPL contains two training stages. In the first stage, the teacher network gives the unlabeled data with pseudo-labels that are divided into the easy and hard groups. The labeled data and the unlabeled data in the easy group with their perturbation are both used to train for a better-performing student network. In the second stage, the unlabeled data in the hard group are predicted by the obtained student network, so the refined pseudo-labeled data are enlarged. All the pseudo-labeling data and labeled data with their perturbation are used to retrain the student network, progressively improving the defect feature representation. We build a mobile screen defect dataset (MSDD-3) with three classes of defects. PPL is implemented on MSDD-3 as well as other public datasets. Extensive experimental results demonstrate that PPL significantly surpasses the state-of-the-art methods across all evaluation partition protocols.Keywords
Funding Information
- National Key Research and Development Program of China (2020AAA0108300)
- National Natural Science Foundation of China (62176092, 62176224, 62222602, 62306165)
- Natural Science Foundation of Chongqing Municipality (CSTB2023NSCQJQX0007)
- China Postdoctoral Science Foundation (2023M731957)
- China Computer Federation (CCF)-Lenovo Blue Ocean Research Fund
This publication has 60 references indexed in Scilit:
- SMD LED chips defect detection using a YOLOv3-dense modelAdvanced Engineering Informatics, 2021
- Guided Collaborative Training for Pixel-Wise Semi-Supervised Learning2020
- Segmentation-based deep-learning approach for surface-defect detectionJournal of Intelligent Manufacturing, 2019
- Surface defect saliency of magnetic tileThe Visual Computer, 2018
- A fast and robust convolutional neural network-based defect detection model in product quality controlThe International Journal of Advanced Manufacturing Technology, 2017
- Detection of surface cutting defect on magnet using Fourier image reconstructionJournal of Central South University, 2016
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- Visualizing and Understanding Convolutional Networks2014
- A noise robust method based on completed local binary patterns for hot-rolled steel strip surface defectsApplied Surface Science, 2013
- Support-vector networksMachine Learning, 1995