Adaptation Art Image Style Transfer by Integrating CSDA-FD Algorithm and OSDA-DS Algorithm

• Autorzy: Wang Peng

Identyfikatory

DOI

10.22630/MGV.2025.34.4.3

• Języki publikacji: EN

Abstrakty

EN

Traditional domain adaptation learning methods have a strong dependence on data labels. The transfer process can easily lead to a decrease in training set performance, affecting the effectiveness of transfer learning. Therefore, this study proposes a domain adaptation model that combines feature disentangling and disentangling subspaces. The model separates the content and style features of im-ages through disentangling, effectively improving the quality of image transfer. From the results, the proposed feature disentangling algorithm achieved pixel accuracy of over 84% for semantic segmentation of 14 categories, including roads, sidewalks, and buildings, with an average pixel accuracy of 85.2%. On the ImageNet, the precision, recall, F1score, and overall accuracy of the research algorithm were 0.942,0.898, 0.854, and 0.841, respectively. Compared with the One-Class Support Vector Machine, the precision, recall, F1, and overall accuracy were improved by 8.4%, 10.3%, 27.8%, and 10.9%, respectively. The proposed model can accurately recognize and classify images, providing effective technical support for image transfer.

Słowa kluczowe

EN

image style transfer; deep domain adaptation; feature disentangling; domain shift

• Wydawca: Institute of Information Technology of the Warsaw University of Life Sciences – SGGW
• Czasopismo: Machine Graphics and Vision
• Rocznik: 2025
• Tom: Vol. 34, No. 4
• Strony: 43--63
• Opis fizyczny: Bibliogr. 30 poz., fot., rys., tab., wykr.

Twórcy

autor

Wang Peng

• Liaoning Police College, Dalian, China

• https://orcid.org/0009-0001-8934-0524

Bibliografia

• [1] V. Belcamino, A. Carfì, and F. Mastrogiovanni. A systematic review on custom data gloves. IEEE Transactions on Human-Machine Systems 54(5):520-535, 2024. doi:10.1109/THMS.2024.3394674.
• [2] H. Cheng, Y. Wang, H. Li, A. C. Kot, and B. Wen. Disentangled feature representation for few-shot image classification. IEEE Transactions on Neural Networks and Learning Systems 35(8):10422-10435, 2024. doi:10.1109/TNNLS.2023.3241919.
• [3] M. Cotogni, M. Arazzi, and C. Cusano. PhotoStyle60: A photographic style dataset for photo authorship attribution and photographic style transfer. IEEE Transactions on Multimedia 26(6):10573-10584, 2024. doi:10.1109/TMM.2024.3408683.
• [4] Y. Feng, J. Chen, S. He, T. Pan, and Z. Zhou. Globally localized multisource domain adaptation for cross-domain fault diagnosis with category shift. IEEE Transactions on Neural Networks and Learning Systems 34(6):3082-3096, 2023. doi:10.1109/TNNLS.2021.3111732.
• [5] Y. Gao, S. Ma, and J. Liu. DCDR-GAN: A densely connected disentangled representation generative adversarial network for infrared and visible image fusion. IEEE Transactions on Circuits and Systems for Video Technology 33(2):549-561, 2023. doi:10.1109/TCSVT.2022.3206807.
• [6] T. He, C. Shen, and A. van den Hengel. Dynamic convolution for 3D point cloud instance segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence 45(5):5697-5711, 2023. doi:10.1109/TPAMI.2022.3216926.
• [7] W. Hu, H. Song, F. Zhang, Y. Zhao, and X. Shi. Style transfer of Thangka images highlighting style attributes. IEEE Access 11(9):104817-104829, 2023. doi:10.1109/ACCESS.2023.3318258.
• [8] J. Huang, W. Yan, G. Li, T. Li, and S. Liu. Learning disentangled representation for multi-view 3D object recognition. IEEE Transactions on Circuits and Systems for Video Technology 32(2):646-659, 2022. doi:10.1109/TCSVT.2021.3062190.
• [9] G. Kang, L. Jiang, Y. Wei, Y. Yang, and A. Hauptmann. Contrastive adaptation network for single- and multi-source domain adaptation. IEEE Transactions on Pattern Analysis and Machine Intelligence 44(4):1793-1804, 2022. doi:10.1109/TPAMI.2020.3029948.
• [10] J. Li, Y. Xiang, H. Wu, S. Yao, and D. Xu. Optimal transport-based patch matching for image style transfer. IEEE Transactions on Multimedia 25(9):5927-5940, 2023. doi:10.1109/TMM.2022.3201387.
• [11] M. Li, J. Wang, Y. Chen, Y. Tang, Z. Wu, et al. Low-dose CT image synthesis for domain adaptation imaging using a generative adversarial network with noise encoding transfer learning. IEEE Transactions on Medical Imaging 42(9):2616-2630, 2023. doi:10.1109/TMI.2023.3261822.
• [12] Y. S. Liao and C. R. Huang. Semantic context-aware image style transfer. IEEE Transactions on Image Processing 31:1911-1923, 2022. doi:10.1109/TIP.2022.3149237.
• [13] Z. Lin, Z. Wang, H. Chen, X. Ma, C. Xie, et al. Image style transfer algorithm based on semantic segmentation. IEEE Access 9(1):54518-54529, 2021. doi:10.1109/ACCESS.2021.3054969.
• [14] Y. Liu, X. Kang, Y. Huang, K. Wang, and G. Yang. Unsupervised domain adaptation semantic segmentation for remote-sensing images via covariance attention. IEEE Geoscience and Remote Sensing Letters 19(7):6513205, 2022. doi:10.1109/LGRS.2022.3189044.
• [15] Z. Liu, G. Chen, Z. Li, S. Qu, A. Knoll, et al. D2IFLN: Disentangled domain-invariant feature learning networks for domain generalization. IEEE Transactions on Cognitive and Developmental Systems 15(4):2269-2281, 2023. doi:10.1109/TCDS.2023.3264615.
• [16] Z. Ma, T. Lin, X. Li, F. Li, D. He, et al. Dual-affinity style embedding network for semantic-aligned image style transfer. IEEE Transactions on Neural Networks and Learning Systems 34(10):7404-7417, 2023. doi:10.1109/TNNLS.2022.3143356.
• [17] A. Mao, C. Dai, Q. Liu, J. Yang, L. Gao, et al. STD-Net: Structure-preserving and topology-adaptive deformation network for single-view 3D reconstruction. IEEE Transactions on Visualization and Computer Graphics 29(3):1785-1798, 2023. doi:10.1109/TVCG.2021.3131712.
• [18] W. Mao, S. Yang, H. Shi, J. Liu, and Z. Wang. Intelligent typography: Artistic text style transfer for complex texture and structure. IEEE Transactions on Multimedia 25:6485-6498, 2023. doi:10.1109/TMM.2022.3209870.
• [19] H. Mun, G. J. Yoon, J. Song, and S. M. Yoon. Texture preserving photo style transfer network. IEEE Transactions on Multimedia 24(8):3823-3834, 2022. doi:10.1109/TMM.2021.3108401.
• [20] M. Pan, Y. Tang, and H. Li. State-of-the-art in data gloves: A review of hardware, algorithms, and applications. IEEE Transactions on Instrumentation and Measurement 72(2):4002515, 2023. doi:10.1109/TIM.2023.3243614.
• [21] T. Shermin, G. Lu, S. W. Teng, M. Murshed, and F. Sohel. Adversarial network with multiple classifiers for open set domain adaptation. IEEE Transactions on Multimedia 23:2732-2744, 2021. doi:10.1109/TMM.2020.3016126.
• [22] Y. Tang, M. Pan, H. Li, and X. Cao. A convolutional-transformer-based approach for dynamic gesture recognition of data gloves. IEEE Transactions on Instrumentation and Measurement 73(5):2518813, 2024. doi:10.1109/TIM.2024.3400361.
• [23] Q. Wang, S. Li, Z. Wang, X. Zhang, and G. Feng. Multi-source style transfer via style disentanglement network. IEEE Transactions on Multimedia 26:1373-1383, 2024. doi:10.1109/TMM.2023.3281087.
• [24] Z. Wang, X. Zhou, Z. Zhou, Y. Zhang, Y. Zhang, et al. MateJam: Multi-material teeth-clutching layer jamming actuation for soft haptic glove. IEEE Transactions on Haptics 16(2):276-286, 2023. doi:10.1109/TOH.2023.3269063.
• [25] H. Wu, Y. Han, Q. Zhu, and Z. Geng. Novel feature-disentangled autoencoder integrating residual network for industrial soft sensor. IEEE Transactions on Industrial Informatics 19(10):10299-10308, 2023. doi:10.1109/TII.2023.3240923.
• [26] K. Wu, M. Wu, Z. Chen, R. Jin, W. Cui, et al. Reinforced adaptation network for partial domain adaptation. IEEE Transactions on Circuits and Systems for Video Technology 33(5):2370-2380, 2023. doi:10.1109/TCSVT.2022.3223950.
• [27] X. Wu, J. Chen, F. Yu, M. Yao, and J. Luo. Joint learning of multiple latent domains and deep representations for domain adaptation. IEEE Transactions on Cybernetics 51(5):2676-2687, 2021. doi:10.1109/TCYB.2019.2921559.
• [28] J. Zhang, X. Li, H. Li, H. Wang, J. Zhang, et al. Leader-follower control of rehabilitative soft glove based on collaborative sensing and fine motion recognition. IEEE Sensors Journal 24(19):30329-30339, 2024. doi:10.1109/JSEN.2024.3435491.
• [29] R. Zhang, T. Kong, W. Wang, X. Han, and M. You. 3D part assembly generation with instance encoded transformer. IEEE Robotics and Automation Letters 7(4):9051-9058, 2022. doi:10.1109/LRA.2022.3188098.
• [30] Z. Zhou, Y. Wu, X. Yang, and Y. Zhou. Neural style transfer with adaptive auto-correlation alignment loss. IEEE Signal Processing Letters 29:1027-1031, 2022. doi:10.1109/LSP.2022.3165758.