YANG, Wenjia ;ZHOU, Youhang ;MENG, Gaolei ;LI, Yuze ;GONG, Tianyu . Improving the efficiency of steel plate surface defect classification by reducing the labeling cost using deep active learning method. Articles in Press, [S.l.], v. 0, n.0, p. , october 2024. ISSN 0039-2480. Available at: <https://www.sv-jme.eu/sl/article/improving-the-efficiency-of-steel-plate-surface-defect-classification-by-reducing-the-labeling-cost-using-deep-active-learning-method/>. Date accessed: 28 oct. 2024. doi:http://dx.doi.org/.
Yang, W., Zhou, Y., MENG, G., Li, Y., & Gong, T. (0). Improving the efficiency of steel plate surface defect classification by reducing the labeling cost using deep active learning method. Articles in Press, 0(0), . doi:http://dx.doi.org/
@article{., author = {Wenjia Yang and Youhang Zhou and Gaolei MENG and Yuze Li and Tianyu Gong}, title = {Improving the efficiency of steel plate surface defect classification by reducing the labeling cost using deep active learning method}, journal = {Articles in Press}, volume = {0}, number = {0}, year = {0}, keywords = {}, abstract = {Efficient surface defects classification is one of the research hotpots in steel plate defect recognition. Compared with traditional methods, deep learning methods have been effective in improving classification accuracy and efficiency, but it requires a large amount of labeled data, resulting in limited improvement of detection efficiency. The active learning, using both labeled and unlabeled samples for model training, can alleviate this labeling effort. To reduce the labeling effort under the premise of satisfying the classification accuracy, a deep active learning method is proposed for steel plate surface defects classification. Firstly, a lightweight convolutional neural network is designed, which speeds up the training process and enhance the model regularization. Secondly, a novel uncertainty-based sampling strategy, which calculates KL-divergence between two kinds of distributions, is used as an uncertainty measure to select new samples for labeling. Finally, the performance of the proposed method is validated using the steel surface defects dataset from Northeastern University (NEU-CLS) and the milling steel surface defects dataset from a local laboratory. The experimental results show that the proposed method can achieve steel surface defects classification accuracy of not less than 92% with no more than 50% of the dataset to be labeled, which indicates that this method has potential application in sur-face defect classification of industrial products.}, issn = {0039-2480}, pages = {}, doi = {}, url = {https://www.sv-jme.eu/sl/article/improving-the-efficiency-of-steel-plate-surface-defect-classification-by-reducing-the-labeling-cost-using-deep-active-learning-method/} }
Yang, W.,Zhou, Y.,MENG, G.,Li, Y.,Gong, T. 0 October 0. Improving the efficiency of steel plate surface defect classification by reducing the labeling cost using deep active learning method. Articles in Press. [Online] 0:0
%A Yang, Wenjia %A Zhou, Youhang %A MENG, Gaolei %A Li, Yuze %A Gong, Tianyu %D 0 %T Improving the efficiency of steel plate surface defect classification by reducing the labeling cost using deep active learning method %B 0 %9 %! Improving the efficiency of steel plate surface defect classification by reducing the labeling cost using deep active learning method %K %X Efficient surface defects classification is one of the research hotpots in steel plate defect recognition. Compared with traditional methods, deep learning methods have been effective in improving classification accuracy and efficiency, but it requires a large amount of labeled data, resulting in limited improvement of detection efficiency. The active learning, using both labeled and unlabeled samples for model training, can alleviate this labeling effort. To reduce the labeling effort under the premise of satisfying the classification accuracy, a deep active learning method is proposed for steel plate surface defects classification. Firstly, a lightweight convolutional neural network is designed, which speeds up the training process and enhance the model regularization. Secondly, a novel uncertainty-based sampling strategy, which calculates KL-divergence between two kinds of distributions, is used as an uncertainty measure to select new samples for labeling. Finally, the performance of the proposed method is validated using the steel surface defects dataset from Northeastern University (NEU-CLS) and the milling steel surface defects dataset from a local laboratory. The experimental results show that the proposed method can achieve steel surface defects classification accuracy of not less than 92% with no more than 50% of the dataset to be labeled, which indicates that this method has potential application in sur-face defect classification of industrial products. %U https://www.sv-jme.eu/sl/article/improving-the-efficiency-of-steel-plate-surface-defect-classification-by-reducing-the-labeling-cost-using-deep-active-learning-method/ %0 Journal Article %R %& %P 1 %J Articles in Press %V 0 %N 0 %@ 0039-2480 %8 2024-10-08 %7 2024-10-08
Yang, Wenjia, Youhang Zhou, Gaolei MENG, Yuze Li, & Tianyu Gong. "Improving the efficiency of steel plate surface defect classification by reducing the labeling cost using deep active learning method." Articles in Press [Online], 0.0 (0): . Web. 28 Oct. 2024
TY - JOUR AU - Yang, Wenjia AU - Zhou, Youhang AU - MENG, Gaolei AU - Li, Yuze AU - Gong, Tianyu PY - 0 TI - Improving the efficiency of steel plate surface defect classification by reducing the labeling cost using deep active learning method JF - Articles in Press DO - KW - N2 - Efficient surface defects classification is one of the research hotpots in steel plate defect recognition. Compared with traditional methods, deep learning methods have been effective in improving classification accuracy and efficiency, but it requires a large amount of labeled data, resulting in limited improvement of detection efficiency. The active learning, using both labeled and unlabeled samples for model training, can alleviate this labeling effort. To reduce the labeling effort under the premise of satisfying the classification accuracy, a deep active learning method is proposed for steel plate surface defects classification. Firstly, a lightweight convolutional neural network is designed, which speeds up the training process and enhance the model regularization. Secondly, a novel uncertainty-based sampling strategy, which calculates KL-divergence between two kinds of distributions, is used as an uncertainty measure to select new samples for labeling. Finally, the performance of the proposed method is validated using the steel surface defects dataset from Northeastern University (NEU-CLS) and the milling steel surface defects dataset from a local laboratory. The experimental results show that the proposed method can achieve steel surface defects classification accuracy of not less than 92% with no more than 50% of the dataset to be labeled, which indicates that this method has potential application in sur-face defect classification of industrial products. UR - https://www.sv-jme.eu/sl/article/improving-the-efficiency-of-steel-plate-surface-defect-classification-by-reducing-the-labeling-cost-using-deep-active-learning-method/
@article{{}{.}, author = {Yang, W., Zhou, Y., MENG, G., Li, Y., Gong, T.}, title = {Improving the efficiency of steel plate surface defect classification by reducing the labeling cost using deep active learning method}, journal = {Articles in Press}, volume = {0}, number = {0}, year = {0}, doi = {}, url = {https://www.sv-jme.eu/sl/article/improving-the-efficiency-of-steel-plate-surface-defect-classification-by-reducing-the-labeling-cost-using-deep-active-learning-method/} }
TY - JOUR AU - Yang, Wenjia AU - Zhou, Youhang AU - MENG, Gaolei AU - Li, Yuze AU - Gong, Tianyu PY - 2024/10/08 TI - Improving the efficiency of steel plate surface defect classification by reducing the labeling cost using deep active learning method JF - Articles in Press; Vol 0, No 0 (0): Articles in Press DO - KW - N2 - Efficient surface defects classification is one of the research hotpots in steel plate defect recognition. Compared with traditional methods, deep learning methods have been effective in improving classification accuracy and efficiency, but it requires a large amount of labeled data, resulting in limited improvement of detection efficiency. The active learning, using both labeled and unlabeled samples for model training, can alleviate this labeling effort. To reduce the labeling effort under the premise of satisfying the classification accuracy, a deep active learning method is proposed for steel plate surface defects classification. Firstly, a lightweight convolutional neural network is designed, which speeds up the training process and enhance the model regularization. Secondly, a novel uncertainty-based sampling strategy, which calculates KL-divergence between two kinds of distributions, is used as an uncertainty measure to select new samples for labeling. Finally, the performance of the proposed method is validated using the steel surface defects dataset from Northeastern University (NEU-CLS) and the milling steel surface defects dataset from a local laboratory. The experimental results show that the proposed method can achieve steel surface defects classification accuracy of not less than 92% with no more than 50% of the dataset to be labeled, which indicates that this method has potential application in sur-face defect classification of industrial products. UR - https://www.sv-jme.eu/sl/article/improving-the-efficiency-of-steel-plate-surface-defect-classification-by-reducing-the-labeling-cost-using-deep-active-learning-method/
Yang, Wenjia, Zhou, Youhang, MENG, Gaolei, Li, Yuze, AND Gong, Tianyu. "Improving the efficiency of steel plate surface defect classification by reducing the labeling cost using deep active learning method" Articles in Press [Online], Volume 0 Number 0 (08 October 2024)
Articles in Press
Efficient surface defects classification is one of the research hotpots in steel plate defect recognition. Compared with traditional methods, deep learning methods have been effective in improving classification accuracy and efficiency, but it requires a large amount of labeled data, resulting in limited improvement of detection efficiency. The active learning, using both labeled and unlabeled samples for model training, can alleviate this labeling effort. To reduce the labeling effort under the premise of satisfying the classification accuracy, a deep active learning method is proposed for steel plate surface defects classification. Firstly, a lightweight convolutional neural network is designed, which speeds up the training process and enhance the model regularization. Secondly, a novel uncertainty-based sampling strategy, which calculates KL-divergence between two kinds of distributions, is used as an uncertainty measure to select new samples for labeling. Finally, the performance of the proposed method is validated using the steel surface defects dataset from Northeastern University (NEU-CLS) and the milling steel surface defects dataset from a local laboratory. The experimental results show that the proposed method can achieve steel surface defects classification accuracy of not less than 92% with no more than 50% of the dataset to be labeled, which indicates that this method has potential application in sur-face defect classification of industrial products.