{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,23]],"date-time":"2026-03-23T09:06:31Z","timestamp":1774256791116,"version":"3.50.1"},"reference-count":27,"publisher":"PeerJ","license":[{"start":{"date-parts":[[2026,3,23]],"date-time":"2026-03-23T00:00:00Z","timestamp":1774224000000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Shanxi Federation of Social Sciences under the 2025 Youth Art Research Special Program","award":["SXQSNMS2025003"],"award-info":[{"award-number":["SXQSNMS2025003"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"abstract":"<jats:p>Artistic style transfer aims to repaint the content image with the learned artistic style. Despite notable progress achieved by convolutional neural network (CNN)-based methods, existing approaches often suffer from complex loss landscapes and limited generalization, particularly under data-scarce settings. To address these challenges, we propose a novel style transfer framework that explicitly integrates domain adaptation principles with Sharpness-Aware Minimization (SAM). Unlike previous methods, our approach aligns high-dimensional feature representations between content and style domains to preserve semantic structure, while enabling flexible stylistic transformations through controlled texture and appearance modulation in lower-dimensional spaces. Furthermore, SAM is employed to smooth the optimization landscape, leading to more stable training dynamics and improved generalization. Extensive experiments conducted on the WikiArt and DIV2k datasets show that the proposed method consistently outperforms state-of-the-art techniques, achieving a 0.0286 improvement over Cascade Style Transfer (CST) in the CLIP Score metric, while producing visually clearer and more coherent stylized results. Notably, our framework shows strong advantages in small-sample style transfer scenarios, where traditional methods typically degrade. These results indicate that the proposed method provides a robust and efficient solution for artistic style transfer with enhanced stability and generalization.<\/jats:p>","DOI":"10.7717\/peerj-cs.3720","type":"journal-article","created":{"date-parts":[[2026,3,23]],"date-time":"2026-03-23T08:26:10Z","timestamp":1774254370000},"page":"e3720","source":"Crossref","is-referenced-by-count":0,"title":["Improving aesthetic pattern-aware style transfer networks with Sharpness-Aware Minimization"],"prefix":"10.7717","volume":"12","author":[{"given":"Jinguang","family":"Lv","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nali","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"4443","published-online":{"date-parts":[[2026,3,23]]},"reference":[{"key":"10.7717\/peerj-cs.3720\/ref-1","first-page":"126","article-title":"NTIRE 2017 challenge on single image super-resolution: dataset and study","author":"Agustsson","year":"2017"},{"key":"10.7717\/peerj-cs.3720\/ref-2","first-page":"862","article-title":"ArtFlow: unbiased image style transfer via reversible neural flows","author":"An","year":"2021"},{"key":"10.7717\/peerj-cs.3720\/ref-3","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2110.03141","article-title":"Efficient sharpness-aware minimization for improved training of neural networks","author":"Du","year":"2021"},{"key":"10.7717\/peerj-cs.3720\/ref-4","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.01412","article-title":"Sharpness-aware minimization for efficiently improving generalization","author":"Foret","year":"2020"},{"key":"10.7717\/peerj-cs.3720\/ref-5","first-page":"2414","article-title":"Image style transfer using convolutional neural networks","author":"Gatys","year":"2016"},{"key":"10.7717\/peerj-cs.3720\/ref-6","doi-asserted-by":"publisher","first-page":"3985","DOI":"10.1109\/CVPR.2017.397","article-title":"Controlling perceptual factors in neural style transfer","author":"Gatys","year":"2017"},{"key":"10.7717\/peerj-cs.3720\/ref-7","first-page":"1501","article-title":"Arbitrary style transfer in real-time with adaptive instance normalization","author":"Huang","year":"2017"},{"key":"10.7717\/peerj-cs.3720\/ref-8","first-page":"694","article-title":"Perceptual losses for real-time style transfer and super-resolution","author":"Johnson","year":"2016"},{"key":"10.7717\/peerj-cs.3720\/ref-9","first-page":"10051","article-title":"Style transfer by relaxed optimal transport and self-similarity","author":"Kolkin","year":"2019"},{"key":"10.7717\/peerj-cs.3720\/ref-10","first-page":"18062","article-title":"CLIPstyler: image style transfer with a single text condition","author":"Kwon","year":"2022"},{"key":"10.7717\/peerj-cs.3720\/ref-11","article-title":"Universal style transfer via feature transforms","volume-title":"Advances in Neural Information Processing Systems 30","author":"Li","year":"2017"},{"key":"10.7717\/peerj-cs.3720\/ref-12","first-page":"3809","article-title":"Learning linear transformations for fast image and video style transfer","author":"Li","year":"2019"},{"key":"10.7717\/peerj-cs.3720\/ref-13","first-page":"453","article-title":"A closed-form solution to photorealistic image stylization","author":"Li","year":"2018"},{"key":"10.7717\/peerj-cs.3720\/ref-14","first-page":"7880","article-title":"ManiGAN: text-guided image manipulation","author":"Li","year":"2020"},{"issue":"3","key":"10.7717\/peerj-cs.3720\/ref-15","doi-asserted-by":"publisher","first-page":"593","DOI":"10.2308\/iace-50038","article-title":"Wiki Art Gallery, Inc.: a case for critical thinking","volume":"26","author":"Phillips","year":"2011","journal-title":"Issues in Accounting Education"},{"key":"10.7717\/peerj-cs.3720\/ref-16","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"10.7717\/peerj-cs.3720\/ref-17","first-page":"234","article-title":"U-Net: convolutional networks for biomedical image segmentation","author":"Ronneberger","year":"2015"},{"key":"10.7717\/peerj-cs.3720\/ref-18","first-page":"6924","article-title":"Improved texture networks: maximizing quality and diversity in feed-forward stylization and texture synthesis","author":"Ulyanov","year":"2017"},{"key":"10.7717\/peerj-cs.3720\/ref-19","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1016\/j.neucom.2018.05.083","article-title":"Deep visual domain adaptation: a survey","volume":"312","author":"Wang","year":"2018","journal-title":"Neurocomputing"},{"key":"10.7717\/peerj-cs.3720\/ref-20","first-page":"1316","article-title":"AttnGAN: fine-grained text to image generation with attentional generative adversarial networks","author":"Xu","year":"2018"},{"key":"10.7717\/peerj-cs.3720\/ref-21","first-page":"9036","article-title":"Photorealistic style transfer via wavelet transforms","author":"Yoo","year":"2019"},{"key":"10.7717\/peerj-cs.3720\/ref-22","first-page":"2720","article-title":"Universal domain adaptation","author":"You","year":"2019"},{"key":"10.7717\/peerj-cs.3720\/ref-23","first-page":"5907","article-title":"StackGAN: text to photo-realistic image synthesis with stacked generative adversarial networks","author":"Zhang","year":"2017"},{"key":"10.7717\/peerj-cs.3720\/ref-24","doi-asserted-by":"publisher","first-page":"112959","DOI":"10.1016\/j.knosys.2025.112959","article-title":"DyArtbank: diverse artistic style transfer via pre-trained stable diffusion and dynamic style prompt artbank","volume":"310","author":"Zhang","year":"2025","journal-title":"Knowledge-Based Systems"},{"key":"10.7717\/peerj-cs.3720\/ref-25","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2404.11474","article-title":"Towards highly realistic artistic style transfer via stable diffusion with step-aware and layer-aware prompt","author":"Zhang","year":"2024a"},{"key":"10.7717\/peerj-cs.3720\/ref-26","doi-asserted-by":"publisher","first-page":"7396","DOI":"10.1609\/aaai.v38i7.28570","article-title":"ArtBank: artistic style transfer with pre-trained diffusion model and implicit style prompt bank","volume":"38","author":"Zhang","year":"2024b","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"10.7717\/peerj-cs.3720\/ref-27","first-page":"2223","article-title":"Unpaired image-to-image translation using cycle-consistent adversarial networks","author":"Zhu","year":"2017"}],"container-title":["PeerJ Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/peerj.com\/articles\/cs-3720.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-3720.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-3720.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-3720.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,23]],"date-time":"2026-03-23T08:26:12Z","timestamp":1774254372000},"score":1,"resource":{"primary":{"URL":"https:\/\/peerj.com\/articles\/cs-3720"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,23]]},"references-count":27,"alternative-id":["10.7717\/peerj-cs.3720"],"URL":"https:\/\/doi.org\/10.7717\/peerj-cs.3720","archive":["CLOCKSS","LOCKSS","Portico"],"relation":{},"ISSN":["2376-5992"],"issn-type":[{"value":"2376-5992","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,23]]},"article-number":"e3720"}}