System Design and Development for Industry-Education Integration in Art Universities Based on Generative Adversarial Networks and Attention Mechanism
DOI:
https://doi.org/10.4108/eetsis.10217Keywords:
generative adversarial network, attention mechanism, multi-head self-attention, WGAN, art resource generationAbstract
This study focuses on the algorithm design and system development of Generative Adversarial Networks and attention mechanisms in the context of industry-education integration at art universities. To address issues such as training instability, missing details, and insufficient personalization in the intelligent generation of art resources, a hybrid algorithm architecture integrating multi-head self-attention mechanisms and Wasserstein distance optimization is proposed. The generator incorporates multi-scale feature extraction and local-global joint attention mechanisms, significantly enhancing the style consistency and detail expression in image generation. The discriminator combines gradient penalty strategies to enhance the model's training stability. The study trains and evaluates using the COCO and ArtBench datasets, achieving excellent results in terms of generation quality, computational efficiency, and diversity. The highest image quality score is 94.8, and the diversity score is 92.1. The experimental results demonstrate the effectiveness of the designed algorithm in meeting the customized and high-quality resource generation needs of art universities, providing reliable technical support and application foundation for intelligent content generation in industry-education integration.
References
[1] Goodfellow I., Pouget-Abadie J., Mirza M., et al. Generative adversarial nets. Advances in Neural Information Processing Systems. 2014, 27:2672-2680.
[2] Radford A., Metz L., Chintala S., et al. Unsupervised representation learning with deep convolutional generative adversarial networks. International Conference on Learning Representations. 2016, 1(1):1-16.
[3] Karras T., Laine S., Aila T., et al. A style-based generator architecture for generative adversarial networks. IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2019, 4401-4410.
[4] Dosovitskiy A., Beyer L., Kolesnikov A., et al. An image is worth 16x16 words: Transformers for image recognition at scale. International Conference on Learning Representations. 2021, 1(1):1-16.
[5] Vaswani A., Shazeer N., Parmar N., et al. Attention is all you need. Advances in Neural Information Processing Systems. 2017, 30:5998-6008.
[6] Zhang H., Goodfellow I., Metaxas D., et al. Self-attention generative adversarial networks. International Conference on Machine Learning. 2019, 97:7354-7363.
[7] Chen M., Radford A., Child R., et al. Generative pretraining from pixels. International Conference on Machine Learning. 2020, 119:1691-1703.
[8] Chen Yongchao, He Yanqi, Liu Yang, et al. A low-light image enhancement algorithm based on generative adversarial networks. Computer Engineering and Science. 2025, 1:1-9.
[9] Chen Xian, Feng Lin, Chen Bing, et al. Cloud removal of remote sensing images by integrating cloud distortion and generative adversarial networks. Telecommunications Technology. 2025, 1:1-11.
[10] Wang Lifang, Ren Wenjing, Guo Xiaodong, et al. Multi-path feature generation adversarial network for noise reduction of low-dose CT images. Computer Applications. 2025, 1:1-12.
[11] Jiang Tonghai, Wang Feng, Liu Ziqi, et al. A joint scene generation method for wind and solar meteorological resources based on improved generative adversarial networks. China Electric Power. 2025, 58(03):183-192.
[12] Yang Yu, et al. Application of generative adversarial networks in financial transaction data analysis. Journal of Shanxi University of Finance and Economics. 2025, 47(S1):43-45.
[13] Feng Shuangshuang, Fan Sha, Deng Chao, et al. Pedestrian abnormal behavior detection based on multi-scale enhanced generative adversarial networks. Computer Engineering and Application. 2025, 1:1-12.
[14] Jiang Gan, Hu Tianyu, Xiong Binbo, et al. High-performance denoising method for distributed optical fiber acoustic vehicle sensor signals based on adversarial generation networks. Semiconductor Optoelectronics. 2025, 1:1-8.
[15] Chen Zhen, Liu Wei, Lu Ruimin, et al. Poisoning attack on a service quality perception cloud API recommendation system based on generative adversarial networks. Journal of Communications. 2025, 1:1-13.
[16] Zhao Xindong, Liu Chunyu, Wang Chen, et al. A computational imaging method for a simple optical system of a remote sensing camera based on the MsRN-Deblur TransGAN generative adversarial network. Progress in Laser and Optoelectronics. 2025, 1:1-29.
[17] Zhou Hongqiang, Yue Xuan, et al. High-quality integration of industry and education in higher vocational colleges under the new round of the dual high plan. Vocational and Technical Education. 2025, 46(09):46-50.
[18] Jing Yuanjie, Xie Ziliang, Huang Jucheng, et al. The multiple logics of building a governance community for industry-education integration. China Vocational and Technical Education. 2025, (06):61-69.
[19] Jiang Liping, et al. The basic framework and practical approach of digitalization empowering the collaborative governance of industry-education integration community. Education and Vocational. 2025, (06):48-55.
[20] Zhu Xiaobo, Gao Peng, Zhang Shu, et al. An analysis of the entity-based operation model of industry-education integration in local universities. China Science and Technology Forum. 2025, (03):108-116.
[21] Cai Yue, Chen Rong. The value, connotation, and realization path of high-quality textbooks for the integration of industry and education in vocational education. Education and Vocational. 2025, (05):99-105.
[22] Yang Qiu Yue, Li Xiao Feng, et al. A review of the difficulties and solutions in the development of vocational education industry-education integration organizations. Higher Engineering Education Research. 2025, (02):132-137.
[23] Ge Daokai, Xu Shoukun, Shen Jie, et al. Systematic design of deepening industry-education integration reform in ordinary higher education institutions. Research on Higher Engineering Education. 2025, (02):8-13.
[24] Chong M.J., Forsyth D. Effectively unbiased FID and inception score and where to find them. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 2023, (07):21-29.
[25] Taesung Park, Semantic Image Synthesis with Spatially-Adaptive Normalization. CoRR. 2023, (01):114-119.
[26] Aaron Hertzmann. LayoutGAN: Generating Graphic Layouts with Wireframe Discriminators. CoRR. 2025, (02):79-92.
[27] Akash Abdu Jyothi, Thibaut Durand, Jiawei He, Leonid Sigal, Greg Mori. LayoutVAE: Stochastic Scene Layout Generation from a Label Set. CoRR. 2024, (11):55-76.
[28] Alec Radford, Luke Metz, Soumith Chintala. Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks. CoRR. 2025, (01):34-45.
[29] Geoffrey E. Hinton, Oriol Vinyals. Distilling the Knowledge in a Neural Network. CoRR. 2025, (03):07-17.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Xingye Leng, Zhao Yifeng
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
This is an open access article distributed under the terms of the CC BY-NC-SA 4.0, which permits copying, redistributing, remixing, transformation, and building upon the material in any medium so long as the original work is properly cited.
