{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T21:35:42Z","timestamp":1792100142104,"version":"4.4.0"},"reference-count":36,"publisher":"MDPI AG","issue":"5","license":[{"start":{"date-parts":[[2025,5,21]],"date-time":"2025-05-21T00:00:00Z","timestamp":1747785600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Entropy"],"abstract":"<jats:p>To promote the inheritance of traditional culture, a variety of emerging methods rooted in machine learning and deep learning have been introduced. Dunhuang patterns, an important part of traditional Chinese culture, are difficult to collect in large numbers due to their limited availability. However, existing text-to-image methods are computationally intensive and struggle to capture fine details and complex semantic relationships in text and images. To address these challenges, this paper proposes the Diffusion Adapter Network (DANet). It employs a lightweight adapter module to extract visual structural information, enabling the diffusion model to generate Dunhuang patterns with high accuracy, while eliminating the need for expensive fine-tuning of the original model. The attention adapter incorporates a multihead attention module (MHAM) to enhance image modality cues, allowing the model to focus more effectively on key information. A multiscale attention module (MSAM) is employed to capture features at different scales, thereby providing more precise generative guidance. In addition, an adaptive control mechanism (ACM) dynamically adjusts the guidance coefficients across feature layers to further enhance generation quality. In addition, incorporating a cross-entropy loss function enhances the model\u2019s capability in semantic understanding and the classification of Dunhuang patterns. The DANet achieves state-of-the-art (SOTA) performance on the proposed Diversified Dunhuang Patterns Dataset (DDHP). Specifically, it attains a perceptual similarity score (LPIPS) of 0.498, a graph matching score (CLIP score) of 0.533, and a feature similarity score (CLIP-I) of 0.772.<\/jats:p>","DOI":"10.3390\/e27050546","type":"journal-article","created":{"date-parts":[[2025,5,21]],"date-time":"2025-05-21T13:59:43Z","timestamp":1747835983000},"page":"546","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Advancing Traditional Dunhuang Regional Pattern Design with Diffusion Adapter Networks and Cross-Entropy"],"prefix":"10.3390","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-6002-7474","authenticated-orcid":false,"given":"Yihuan","family":"Tian","sequence":"first","affiliation":[{"name":"Department of Space and Culture Design, Kookmin University, Seoul 02707, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-8381-6104","authenticated-orcid":false,"given":"Tao","family":"Yu","sequence":"additional","affiliation":[{"name":"Department of Smart Experience Design, Kookmin University, Seoul 02707, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-1040-6087","authenticated-orcid":false,"given":"Zuling","family":"Cheng","sequence":"additional","affiliation":[{"name":"Department of Global Convergence, Kangwon National University, Chuncheon-si 24341, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sunjung","family":"Lee","sequence":"additional","affiliation":[{"name":"Department of Space and Culture Design, Kookmin University, Seoul 02707, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,5,21]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Chen, Z. (2024). (HTBNet) Arbitrary Shape Scene Text Detection with Binarization of Hyperbolic Tangent and Cross-Entropy. Entropy, 26.","DOI":"10.20944\/preprints202405.1040.v1"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"111013","DOI":"10.1016\/j.patcog.2024.111013","article-title":"Scene Chinese Recognition with Local and Global Attention","volume":"158","author":"Chen","year":"2025","journal-title":"Pattern. Recognit."},{"key":"ref_3","unstructured":"Zhu, J.Y., Zhang, R., Pathak, D., Darrell, T., Efros, A.A., Wang, O., and Shechtman, E. (2017, January 4\u20139). Toward multimodal image-to-image translation. Proceedings of the 31st International Conference on Neural Information Processing Systems, Long Beach, CA, USA."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Xie, Y., and Yang, L. (2018, January 18\u201323). Photographic text-to-image synthesis with a hierarchically-nested adversarial network. Proceedings of the 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognitionm, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00649"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Park, T., Liu, M.Y., Wang, T.C., and Zhu, J.Y. (2019, January 15\u201320). Semantic image synthesis with spatially-adaptive normalization. Proceedings of the 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00244"},{"key":"ref_6","unstructured":"DeVries, T., Romero, A., Pineda, L., Taylor, G.W., and Drozdzal, M. (2019). On the evaluation of conditional GANs. arXiv."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Shen, Y., Liang, J., and Lin, M.C. (2020). GAN-based garment generation using sewing pattern images. Computer Vision\u2013ECCV 2020, Proceedings of the 16th European Conference, Glasgow, UK, 23\u201328 August 2020, Springer International Publishing. Proceedings; Part XVIII 16.","DOI":"10.1007\/978-3-030-58523-5_14"},{"key":"ref_8","first-page":"1","article-title":"Textile image restoration of Chu tombs based on deep learning","volume":"60","author":"Sha","year":"2023","journal-title":"J. Silk"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Chen, Z. (2024). Graph Adaptive Attention Network with Cross-Entropy. Entropy, 26.","DOI":"10.20944\/preprints202406.0939.v1"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Orteu, J.-J., Garcia, D., Robert, L., and Bugarin, F. (2006, January 13\u201315). A speckle texture image generator. Proceedings of the Speckle06: Speckles, from Grains to Flowers, Nimes, France.","DOI":"10.1117\/12.695280"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"012077","DOI":"10.1088\/1757-899X\/864\/1\/012077","article-title":"Facial Expression Transfer using Generative Adversarial Network: A Review","volume":"864","author":"Adibah","year":"2020","journal-title":"IOP Conf. Ser. Mater. Sci. Eng."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"181504","DOI":"10.3788\/LOP57.181504","article-title":"Image Generation Method for Adversarial Network Based on Residual Structure","volume":"57","author":"Yan","year":"2020","journal-title":"Laser Optoelectron. Prog."},{"key":"ref_13","first-page":"1486","article-title":"Deep Generative Image Models Using a Laplacian Pyramid of Adversarial Networks","volume":"Volume 1","author":"Denton","year":"2015","journal-title":"Proceedings of the 29th International Conference on Neural Information Processing Systems"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"252","DOI":"10.1093\/jigpal\/jzaa059","article-title":"Generation of synthetic data with conditional generative adversarial networks","volume":"30","year":"2022","journal-title":"Log. J. IGPL"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Zhang, H., Xu, T., Li, H., Zhang, S., Wang, X., Huang, X., and Metaxas, D. (2017, January 22\u201329). Stackgan: Text to photo-realistic image synthesis with stacked generative adversarial networks. Proceedings of the 2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy.","DOI":"10.1109\/ICCV.2017.629"},{"key":"ref_16","unstructured":"Karras, T., Aila, T., Laine, S., and Lehtinen, J. (2017). Progressive Growing of GANs for Improved Quality, Stability, and Variation. arXiv."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., and Aila, T. (2019). A Style-Based Generator Architecture for Generative Adversarial Networks. arXiv.","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref_18","unstructured":"Brock, A. (2018). Large Scale GAN Training for High Fidelity Natural Image Synthesis. arXiv."},{"key":"ref_19","unstructured":"Nichol, A.Q., and Dhariwal, P. (2021, January 18\u201324). Improved denoising diffusion probabilistic models. Proceedings of the 38th International Conference on Machine Learning, Online."},{"key":"ref_20","unstructured":"Song, J., Meng, C., and Ermon, S. (2020). Denoising diffusion implicit models. arXiv."},{"key":"ref_21","unstructured":"Nichol, A., Dhariwal, P., Ramesh, A., Shyam, P., Mishkin, P., McGrew, B., Sutskever, I., and Chen, M. (2021). Glide: Towards photorealistic image generation and editing with text-guided diffusion models. arXiv."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Chen, Z. (2025). Arbitrary Shape Text Detection with Discrete Cosine Transform and CLIP for Urban Scene Perception in ITS. IEEE Trans. Intell. Transp. Syst., early access.","DOI":"10.1109\/TITS.2025.3534291"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Avrahami, O., Lischinski, D., and Fried, O. (2022, January 18\u201324). Blended diffusion for text-driven editing of natural images. Proceedings of the 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA.","DOI":"10.1109\/CVPR52688.2022.01767"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"767","DOI":"10.3758\/BF03192967","article-title":"Fast-dm: A free program for efficient diffusion model analysis","volume":"39","author":"Voss","year":"2007","journal-title":"Behav. Res. Methods"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"3","DOI":"10.3758\/BF03194023","article-title":"An EZ-diffusion model for response time and accuracy","volume":"14","author":"Wagenmakers","year":"2007","journal-title":"Psychon. Bull. Rev."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Li, X., Liu, Y., Lian, L., Yang, H., Dong, Z., Kang, D., Zhang, S., and Keutzer, K. (2023, January 1\u20136). Q-diffusion: Quantizing diffusion models. Proceedings of the 2023 IEEE\/CVF International Conference on Computer Vision (ICCV), Paris, France.","DOI":"10.1109\/ICCV51070.2023.01608"},{"key":"ref_27","unstructured":"Borji, A. (2022). Generated faces in the wild: Quantitative comparison of stable diffusion, midjourney and dall-e 2. arXiv."},{"key":"ref_28","first-page":"109","article-title":"A Forward-Looking Vision to Employ Artificial Intelligence to Preserve Cultural Heritage","volume":"12","author":"Eyadah","year":"2024","journal-title":"Humanities"},{"key":"ref_29","first-page":"185","article-title":"The role of artificial intelligence and machine learning in preserving cultural heritage and art works via virtual restoration","volume":"10","author":"Gaber","year":"2023","journal-title":"ISPRS Ann. Photogramm. Remote Sens. Spat. Inf. Sci."},{"key":"ref_30","first-page":"111","article-title":"Research on innovative applications of AI technology in the field of cultural heritage conservation","volume":"7","author":"Dandan","year":"2024","journal-title":"Acad. J. Humanit. Soc. Sci."},{"key":"ref_31","first-page":"7596991","article-title":"Application of traditional culture in intelligent advertising design system in the internet era","volume":"2022","author":"Sun","year":"2022","journal-title":"Sci. Program."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"375","DOI":"10.24191\/ajue.v18i2.17992","article-title":"Tradition Meets Modernity: Learning Traditional Building using Artificial Intelligence","volume":"18","author":"Winiarti","year":"2022","journal-title":"Asian J. Univ. Educ."},{"key":"ref_33","unstructured":"Wu, H. (2025, May 14). Innovation of Traditional Culture Development Model in Advertising Design Based on Artificial Intelligence. Available online: https:\/\/www.clausiuspress.com\/article\/3440.html."},{"key":"ref_34","first-page":"58","article-title":"Research on the Design Method of Traditional Decorative Patterns of Ethnic Minorities under the Trend of AIGC","volume":"8","author":"Hu","year":"2023","journal-title":"J. Electron. Inf. Sci."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Hang, W., Alli, H., Hawari, N., and Wang, W. (2024). Artificial Intelligence in Packaging Design: Integrating Traditional Chinese Cultural Elements for Cultural Preservation and Innovation. Int. J. Acad. Res. Bus. Soc. Sci., 1826\u20131836.","DOI":"10.6007\/IJARBSS\/v14-i12\/23689"},{"key":"ref_36","first-page":"7113621","article-title":"Application of Chinese traditional elements in furniture design based on wireless communication and artificial intelligence decision","volume":"2022","author":"Wu","year":"2022","journal-title":"Wirel. Commun. Mob. Comput."}],"container-title":["Entropy"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1099-4300\/27\/5\/546\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T17:38:01Z","timestamp":1760031481000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1099-4300\/27\/5\/546"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,21]]},"references-count":36,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2025,5]]}},"alternative-id":["e27050546"],"URL":"https:\/\/doi.org\/10.3390\/e27050546","relation":{},"ISSN":["1099-4300"],"issn-type":[{"value":"1099-4300","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5,21]]}}}