{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/recognizing-art-style-automatically-in","title":"Recognizing Art Style Automatically in painting with deep learning","arxiv_id":null,"date":"2017-12-21","proceeding":"Proceedings of the Ninth Asian Conference on Machine Learning 2017 12","authors":["Adrian Lecoutre","Benjamin Negrevergne","Florian Yger"],"abstract":"The artistic style (or artistic movement) of a painting is a rich descriptor that captures both\r\nvisual and historical information about the painting. Correctly identifying the artistic style\r\nof a paintings is crucial for indexing large artistic databases. In this paper, we investigate\r\nthe use of deep residual neural to solve the problem of detecting the artistic style of a\r\npainting and outperform existing approaches by almost 10% on the Wikipaintings dataset\r\n(for 25 di\u000berent style). To achieve this result, the network is \frst pre-trained on ImageNet,\r\nand deeply retrained for artistic style. We empirically evaluate that to achieve the best\r\nperformance, one need to retrain about 20 layers. This suggests that the two tasks are as\r\nsimilar as expected, and explain the previous success of hand crafted features. We also\r\ndemonstrate that the style detected on the Wikipaintings dataset are consistent with styles\r\ndetected on an independent dataset and describe a number of experiments we conducted\r\nto validate this approach both qualitatively and quantitatively.","url_abs":"http://proceedings.mlr.press/v77/lecoutre17a.html","url_pdf":"http://proceedings.mlr.press/v77/lecoutre17a/lecoutre17a.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"recognizing-art-style-automatically-in","repo_url":"https://github.com/bnegreve/rasta","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"artistic-style-classification","task_name":"Artistic style classification"},{"task_slug":"deep-learning","task_name":"Deep Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/artistic-style-classification-on-rasta","task":"Artistic style classification","dataset":"RASTA","model":"ResNet50 With bagging","rank_in_archive_order":1,"of":1,"metrics":{"Top-1 Accuracy":"0.611"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}