{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T16:28:35Z","timestamp":1772641715059,"version":"3.50.1"},"reference-count":40,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T00:00:00Z","timestamp":1772582400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:p>In recent years, despite the remarkable performance of large-scale vision language models across various visual classification tasks, their substantial parameter counts and high fine-tuning costs have hindered deployment in resource-constrained cultural and artwork settings. This work specifically addresses the task of object recognition in artwork\u2014that is, identifying semantic objects (e.g., animals, people, everyday items) depicted within paintings, sketches, and other artistic renditions, rather than classifying artistic styles or genres. To address this issue, we propose InfoMSD, an unsupervised, Information-Maximization Self-Distillation framework designed for parameter-efficient fine-tuning on unlabeled artwork imagery while preserving robust performance. Specifically, InfoMSD incorporates a teacher-student architecture in the self-distillation phase, where the teacher model generates pseudo-labels for artworks, and the student model learns from the teacher through cross-entropy. By aligning the student's predictions with the discriminative signals from the teacher's pseudo-labels and simultaneously applying entropy-based regularization to sharpen the probability distribution and balance class coverage, the framework improves both the quality of the pseudo-labels and the discriminative capacity of the model. To enable parameter-efficient fine-tuning, only the layer norm parameters and visual prompts in the student model are updated, while the remaining parameters are frozen, significantly reducing computational overhead. Extensive experimental results on artwork datasets show that InfoMSD achieves accuracy improvements of +6.43 and +3.02% over CLIP zero-shot baselines, while adjusting less than 1% of the model parameters. Compared to existing lightweight distillation methods, InfoMSD achieves average accuracy gains of 1.35 and 0.96%, respectively. Overall, InfoMSD offers a novel, information-theoretic paradigm for unsupervised and efficient fine-tuning in object recognition within artistic imagery, balancing performance and efficiency.<\/jats:p>","DOI":"10.3389\/frai.2026.1721866","type":"journal-article","created":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T11:40:14Z","timestamp":1772624414000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["InfoMSD: an information-maximization self-distillation framework for parameter-efficient fine-tuning on artwork images"],"prefix":"10.3389","volume":"9","author":[{"given":"Feng","family":"Guan","sequence":"first","affiliation":[{"name":"School of Mathematics and Statistics, Southwest University","place":["Chongqing, China"]},{"name":"Postdoctoral Research Center, Beijing Pico Exhibition Management Co. Ltd.","place":["Beijing, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Hong","sequence":"additional","affiliation":[{"name":"Postdoctoral Research Center, Beijing Pico Exhibition Management Co. Ltd.","place":["Beijing, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yong","family":"Wang","sequence":"additional","affiliation":[{"name":"Postdoctoral Research Center, Beijing Pico Exhibition Management Co. Ltd.","place":["Beijing, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2026,3,4]]},"reference":[{"key":"B1","doi-asserted-by":"crossref","first-page":"446","DOI":"10.1007\/978-3-319-10599-4_29","article-title":"\u201cFood-101-mining discriminative components with random forests,\u201d","volume-title":"Computer Vision-ECCV 2014","author":"Bossard","year":"2014"},{"key":"B2","first-page":"3606","article-title":"\u201cDescribing textures in the wild,\u201d","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Cimpoi","year":"2014"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.3233\/JIFS-219407.","article-title":"Computational complexity in explainable decision support system: a review","author":"Ezeji","year":"2024","journal-title":"J. Intell. Fuzzy Syst"},{"key":"B4","first-page":"178","article-title":"\u201cLearning generative visual models from few training examples: an incremental bayesian approach tested on 101 object categories,\u201d","volume-title":"Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshop","author":"Fei-Fei","year":"2004"},{"key":"B5","doi-asserted-by":"publisher","first-page":"581","DOI":"10.1007\/s11263-023-01891-x","article-title":"CLIP-Adapter: better vision-language models with feature adapters","volume":"132","author":"Gao","year":"2023","journal-title":"Int. J. Comput. Vision"},{"key":"B6","doi-asserted-by":"publisher","first-page":"2217","DOI":"10.1109\/JSTARS.2019.2918242","article-title":"EuroSAT: a novel dataset and deep learning benchmark for land use and land cover classification","volume":"12","author":"Helber","year":"2019","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens"},{"key":"B7","first-page":"8917","article-title":"\u201cThe many faces of robustness: a critical analysis of out-of-distribution generalization,\u201d","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)","author":"Hendrycks","year":"2021"},{"key":"B8","first-page":"2790","article-title":"\u201cParameter-efficient transfer learning for NLP,\u201d","author":"Houlsby","year":"2019","journal-title":"Proceedings of the 36th International Conference on Machine Learning"},{"key":"B9","article-title":"\u201cLoRA: Low-rank adaptation of large language models,\u201d","volume-title":"The Tenth International Conference on Learning Representations","author":"Hu","year":"2022"},{"key":"B10","first-page":"23773","article-title":"\u201cLP++: a surprisingly strong linear probe for few-shot clip,\u201d","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Huang","year":"2024"},{"key":"B11","doi-asserted-by":"crossref","first-page":"709","DOI":"10.1007\/978-3-031-19827-4_41","article-title":"\u201cVisual prompt tuning,\u201d","volume-title":"Computer Vision-ECCV 2022","author":"Jia","year":"2022"},{"key":"B12","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1080\/10645578.2022.2129944","article-title":"Creating meaningful museums: a model for museum exhibition user experience","volume":"26","author":"King","year":"2023","journal-title":"Visit. Stud"},{"key":"B13","author":"Krizhevsky","year":"2009","journal-title":"Learning multiple layers of features from tiny images"},{"key":"B14","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/978-3-031-19806-9_1","author":"Lee","year":"2022","journal-title":"Cross-domain Ensemble Distillation for Domain Generalization"},{"key":"B15","doi-asserted-by":"publisher","first-page":"108407","DOI":"10.1016\/j.chb.2024.108407","article-title":"A systematic review of digital transformation technologies in museum exhibition","volume":"161","author":"Li","year":"2024","journal-title":"Comput. Hum. Behav"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2212.00784","article-title":"Improving zero-shot models with label distribution priors","author":"Li","year":"2023","journal-title":"arXiv"},{"key":"B17","first-page":"18501","article-title":"\u201cEfficient test-time adaptation of vision-language model,\u201d","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Liu","year":"2024"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2501.02414","article-title":"Journey into automation: image-derived pavement texture extraction and evaluation","author":"Lu","year":"","journal-title":"arXiv"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2507.03559","article-title":"Predicting asphalt pavement friction using texture-based image indicator","author":"Lu","year":"","journal-title":"arXiv"},{"key":"B20","doi-asserted-by":"publisher","first-page":"130375","DOI":"10.1016\/j.neucom.2025.130375","article-title":"CausalSR: structural causal model-driven super-resolution with counterfactual inference","volume":"646","author":"Lu","year":"","journal-title":"Neurocomputing"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2505.07040","article-title":"Differentiable NMS via sinkhorn matching for end-to-end fabric defect detection","author":"Lu","year":"","journal-title":"arXiv"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1306.5151","article-title":"Fine-grained visual classification of aircraft","author":"Maji","year":"2013","journal-title":"arXiv"},{"key":"B23","first-page":"5765","article-title":"LaFTER: Label-free tuning of zero-shot classifier using language and unlabeled image collections","volume":"36","author":"Mirza","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst"},{"key":"B24","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1111\/muan.12238","article-title":"Classification schemes gone Awry: implications for museum research and exhibition display practices","volume":"44","author":"Mohan","year":"2021","journal-title":"Mus. Anthropol"},{"key":"B25","first-page":"4593","article-title":"\u201cSHAP-based explanation methods: a review for NLP interpretability,\u201d","volume-title":"Proceedings of the 29th International Conference on Computational Linguistics","author":"Mosca","year":"2022"},{"key":"B26","doi-asserted-by":"publisher","first-page":"722","DOI":"10.1109\/ICVGIP.2008.47","article-title":"\u201cAutomated flower classification over a large number of classes,\u201d","author":"Nilsback","year":"2008","journal-title":"2008 Sixth Indian Conference on Computer Vision, Graphics"},{"key":"B27","first-page":"4032","article-title":"\u201cMM-SHAP: a performance-agnostic metric for measuring multimodal contributions in vision and language models & tasks,\u201d","volume-title":"Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics","author":"Parcalabescu","year":"2023"},{"key":"B28","doi-asserted-by":"crossref","first-page":"3498","DOI":"10.1109\/CVPR.2012.6248092","article-title":"\u201cCats and dogs,\u201d","volume-title":"2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Parkhi","year":"2012"},{"key":"B29","first-page":"8748","article-title":"\u201cLearning transferable visual models from natural language supervision,\u201d","author":"Radford","year":"2021","journal-title":"Proceedings of the 38th International Conference on Machine Learning"},{"key":"B30","doi-asserted-by":"crossref","first-page":"1135","DOI":"10.1145\/2939672.2939778","article-title":"\u201c\u2018Why should i trust you?' Explaining the predictions of any classifier,\u201d","volume-title":"Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","author":"Ribeiro","year":"2016"},{"key":"B31","first-page":"618","article-title":"\u201cGrad-CAM: visual explanations from deep networks via gradient-based localization,\u201d","volume-title":"Proceedings of the IEEE International Conference on Computer Vision (ICCV)","author":"Selvaraju","year":"2017"},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1212.0402","article-title":"UCF101: a dataset of 101 human actions classes from videos in the wild","author":"Soomro","year":"2012","journal-title":"arXiv"},{"key":"B33","first-page":"33816","article-title":"\u201cPOUF: Prompt-oriented unsupervised fine-tuning for large pre-trained models,\u201d","volume-title":"Proceedings of the 40th International Conference on Machine Learning","author":"Tanwisuth","year":"2023"},{"key":"B34","first-page":"10506","article-title":"\u201cLearning robust global representations by penalizing local predictive power,\u201d","volume-title":"Advances in Neural Information Processing Systems","author":"Wang","year":"2019"},{"key":"B35","doi-asserted-by":"crossref","first-page":"2595","DOI":"10.1145\/3474085.3475434","article-title":"\u201cEmbracing the dark knowledge: domain generalization using regularized knowledge distillation,\u201d","volume-title":"Proceedings of the 29th ACM International Conference on Multimedia (MM '21)","author":"Wang","year":"2021"},{"key":"B36","first-page":"3485","article-title":"\u201cSUN database: large-scale scene recognition from abbey to zoo,\u201d","volume-title":"2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Xiao","year":"2010"},{"key":"B37","doi-asserted-by":"publisher","first-page":"106312","DOI":"10.1016\/j.jobe.2023.106312","article-title":"A multinomial logistic regression model-based seismic risk assessment method for museum exhibition halls","volume":"69","author":"Yang","year":"2023","journal-title":"J. Build. Eng"},{"key":"B38","article-title":"\u201cBoostAdapter: improving vision-language test-time adaptation via regional bootstrapping,\u201d","volume-title":"Advances in Neural Information Processing Systems 37 (NeurIPS 2024)","author":"Zhang","year":"2024"},{"key":"B39","doi-asserted-by":"publisher","first-page":"2337","DOI":"10.1007\/s11263-022-01653-1","article-title":"Learning to prompt for vision-language models","volume":"130","author":"Zhou","year":"","journal-title":"Int. J. Comput. Vision"},{"key":"B40","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2204.03649","article-title":"Unsupervised prompt learning for vision-language models","author":"Zhou","year":"","journal-title":"arXiv"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1721866\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T11:40:25Z","timestamp":1772624425000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1721866\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,4]]},"references-count":40,"alternative-id":["10.3389\/frai.2026.1721866"],"URL":"https:\/\/doi.org\/10.3389\/frai.2026.1721866","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,4]]},"article-number":"1721866"}}