Appearance defects frequently occur during cigarette manufacturing due to production equipment or raw materials. Appearance defects significantly impact the quality of tobacco products. Since manual inspection cannot keep pace with the demands of high-speed production lines, rapid and accurate automated classification and detection are essential. Supervised learning is predominantly employed in research on automated classification of product quality appearance defects. However, supervised learning necessitates substantial labeled data for training, which is time-consuming to annotate and prone to errors. This paper proposes a self-supervised learning-based classification model for cigarette appearance defects. This is a generative adversarial network (GAN) model based on masked autoencoders (MAE), called MAE-GAN. First, this model combines MAE as a generator with a simple discriminator to form a generative adversarial network according to the principle of mask reconstruction in MAE. The generator reconstructs the images to learn their features. Second, the model also integrates MAE's loss function into the GAN's loss function. This lets the model focus on pixel-level losses during training. As a result, model performance is improved. Third, a Wasserstein GAN with gradient penalty (WGAN-GP) is added to stabilize the training process. In addition, this paper preprocesses cigarette images through segmentation and recombination. Neural networks typically accept images with the same width and height. Due to the narrow shape of cigarette images, if the image is directly transformed into a square and fed into a neural network, the details of the image will be severely lost. This paper segments the cigarette image into three parts and recombines them into images with similar length and width, greatly improving classification accuracy.
Citation: Youliang Zhang, Guowu Yuan, Hao Wu, Hao Zhou. MAE-GAN: a self-supervised learning-based classification model for cigarette appearance defects[J]. Applied Computing and Intelligence, 2024, 4(2): 253-268. doi: 10.3934/aci.2024015
Appearance defects frequently occur during cigarette manufacturing due to production equipment or raw materials. Appearance defects significantly impact the quality of tobacco products. Since manual inspection cannot keep pace with the demands of high-speed production lines, rapid and accurate automated classification and detection are essential. Supervised learning is predominantly employed in research on automated classification of product quality appearance defects. However, supervised learning necessitates substantial labeled data for training, which is time-consuming to annotate and prone to errors. This paper proposes a self-supervised learning-based classification model for cigarette appearance defects. This is a generative adversarial network (GAN) model based on masked autoencoders (MAE), called MAE-GAN. First, this model combines MAE as a generator with a simple discriminator to form a generative adversarial network according to the principle of mask reconstruction in MAE. The generator reconstructs the images to learn their features. Second, the model also integrates MAE's loss function into the GAN's loss function. This lets the model focus on pixel-level losses during training. As a result, model performance is improved. Third, a Wasserstein GAN with gradient penalty (WGAN-GP) is added to stabilize the training process. In addition, this paper preprocesses cigarette images through segmentation and recombination. Neural networks typically accept images with the same width and height. Due to the narrow shape of cigarette images, if the image is directly transformed into a square and fed into a neural network, the details of the image will be severely lost. This paper segments the cigarette image into three parts and recombines them into images with similar length and width, greatly improving classification accuracy.
| [1] |
G. W. Yuan, J. C. Liu, H. Y. Liu, R. Qu, H. Zhou, Cigarette appearance defect classification based on ResNeSt (Chinese), Journal of Yunnan University (Natural Science Edition), 44 (2022), 464–470. https://doi.org/10.7540/j.ynu.20210257 doi: 10.7540/j.ynu.20210257
|
| [2] |
R. Qu, G. W. Yuan, J. C. Liu, H. Zhou, Detection of cigarette appearance defects based on improved SSD model, Proceedings of the 2021 5th International Conference on Electronic Information Technology and Computer Engineering, 2021, 1148–1153. https://doi.org/10.1145/3501409.3501612 doi: 10.1145/3501409.3501612
|
| [3] | H. Y. Liu, G. W. Yuan, Cigarette appearance defect detection method based on improved YOLOv5s, Comput. Technol. Dev., 32 (2022), 161–167. |
| [4] |
G. W. Yuan, J. C. Liu, H. Y. Liu, Y. H. Ma, H. Wu, H. Zhou, Detection of cigarette appearance defects based on improved YOLOv4, Electron. Res. Arch., 31 (2023), 1344–1364. https://doi.org/10.3934/era.2023069 doi: 10.3934/era.2023069
|
| [5] |
H. Y. Liu, G. W. Yuan, L. Yang, K. X. Liu, H. Zhou, An appearance defect detection method for cigarettes based on C-CenterNet, Electronic, 11 (2022), 2182–2182. https://doi.org/10.3390/electronics11142182 doi: 10.3390/electronics11142182
|
| [6] |
Y. H. Ma, G. W. Yuan, K. Yue, H. Zhou, CJS-YOLOv5n: a high-performance detection model for cigarette appearance defects, Math. Biosci. Eng., 20 (2023), 17886–17904. https://doi.org/10.3934/mbe.2023795 doi: 10.3934/mbe.2023795
|
| [7] | Q. Z. Xie, Z. H. Dai, E. Hovy, M. Luong, Q. Le, Unsupervised data augmentation for consistency training, Proceedings of the 34th International Conference on Neural Information Processing Systems, 2020, 6256–6268. |
| [8] |
J. Z. Bengar, J. van de Weijer, B. Twardowski, B. Raducanu, Reducing label effort: self-supervised meets active learning, Proceedings of IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), 2021, 1631–1639. https://doi.org/10.1109/ICCVW54120.2021.00188 doi: 10.1109/ICCVW54120.2021.00188
|
| [9] |
X. Liu, F. J. Zhang, Z. Y. Hou, L. Mian, Z. Y. Wang, J. Zhang, et al., Self-supervised learning: generative or contrastive, IEEE Trans. Knowl. Data Eng., 35 (2023), 857–876. https://doi.org/10.1109/TKDE.2021.3090866 doi: 10.1109/TKDE.2021.3090866
|
| [10] |
S. Kornblith, J. Shlens, Q. V. Le, Do better ImageNet models transfer better? Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019, 2661–2671. https://doi.org/10.1109/CVPR.2019.00277 doi: 10.1109/CVPR.2019.00277
|
| [11] |
Y. W. Li, J. J. Qiao, S. J. Ma, Z. Q. Wu, Q. H. Wu, Research and improvement of cigarette splicing quality of cigarette rolling machine (Chinese), Tobacco Science and Technology, 45 (2012), 24–27. https://doi.org/10.3969/j.issn.1002-0861.2012.10.006 doi: 10.3969/j.issn.1002-0861.2012.10.006
|
| [12] |
L. L. Jing, Y. L. Tian, Self-supervised visual feature learning with deep neural networks: a survey, IEEE Trans. Pattern Anal., 43 (2020), 4037–4058. https://doi.org/10.1109/TPAMI.2020.2992393 doi: 10.1109/TPAMI.2020.2992393
|
| [13] |
K. M. He, X. L. Chen, S. N. Xie, Y. H. Li, P. Dollr, R. Girshick, Masked autoencoders are scalable vision learners, Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023, 16000–16009. https://doi.org/10.1109/CVPR52688.2022.01553 doi: 10.1109/CVPR52688.2022.01553
|
| [14] | Y. Li, S. Xie, X. Chen, P. Dollar, K. He, R. Girshick, Benchmarking detection transfer learning with vision transformers, arXiv: 2111.11429. https://doi.org/10.48550/arXiv.2111.11429 |
| [15] |
K. M. He, H. Q. Fan, Y. X. Wu, S. N. Xie, R. Girshick, Momentum contrast for unsupervised visual representation learning, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020, 9729–9738. https://doi.org/10.1109/CVPR42600.2020.00975 doi: 10.1109/CVPR42600.2020.00975
|
| [16] | I. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, et al., Generative adversarial nets, Proceedings of the 27th International Conference on Neural Information Processing Systems, 2014, 2672–2680. |
| [17] | A. Radford, Unsupervised representation learning with deep convolutional generative adversarial networks, arXiv: 1511.06434. https://doi.org/10.48550/arXiv.1511.06434 |
| [18] | T. Salimans, I. Goodfellow, W. Zaremba, V. Cheung, A. Radford, X. Chen, Improved tech- niques for training gans, Proceedings of the 30th International Conference on Neural Information Processing Systems, 2016, 2234–2242. |
| [19] | M. Arjovsky, S. Chintala, L. Bottou, Wasserstein generative adversarial networks, International Conference on Machine Learning, 2017,214–223. |
| [20] | I. Gulrajani, F. Ahmed, M. Arjovsky, V. Dumoulin, A. C. Courville, Improved training of Wasserstein GANs, Proceedings of the 34th International Conference on Machine Learning, 2017,214–223. |
| [21] | T. Karras, T. Aila, S. Laine, J. Lehtinen, Progressive growing of GANs for improved quality, stability, and variation, arXiv: 1710.10196. https://doi.org/10.48550/arXiv.1710.10196 |
Figures(7) / Tables(6)
Youliang Zhang, Guowu Yuan, Hao Wu, Hao Zhou. MAE-GAN: a self-supervised learning-based classification model for cigarette appearance defects[J]. Applied Computing and Intelligence, 2024, 4(2): 253-268. doi: 10.3934/aci.2024015
DownLoad: