
Recognizing Art Style Automatically in painting with deep learning
Lecoutre, Adrian; Negrevergne, Benjamin; Yger, Florian (2017), Recognizing Art Style Automatically in painting with deep learning, in Noh, Yung-Kyun; Zhang, Min-Ling, Proceedings of the 9th Asian Conference on Machine Learning (ACML 2017), JMLR: Workshop and Conference Proceedings, p. 327-342
View/ Open
Type
Communication / ConférenceDate
2017Conference title
9th Asian Conference on Machine Learning (ACML 2017)Conference date
2017-11Conference city
SeoulConference country
"KoreaBook title
Proceedings of the 9th Asian Conference on Machine Learning (ACML 2017)Book author
Noh, Yung-Kyun; Zhang, Min-LingPublisher
JMLR: Workshop and Conference Proceedings
Pages
327-342
Metadata
Show full item recordAuthor(s)
Lecoutre, AdrianLaboratoire d'analyse et modélisation de systèmes pour l'aide à la décision [LAMSADE]
Negrevergne, Benjamin

Laboratoire d'analyse et modélisation de systèmes pour l'aide à la décision [LAMSADE]
Yger, Florian

Laboratoire d'analyse et modélisation de systèmes pour l'aide à la décision [LAMSADE]
Abstract (EN)
The artistic style (or artistic movement) of a painting is a rich descriptor that captures both visual and historical information about the painting. Correctly identifying the artistic style of a paintings is crucial for indexing large artistic databases. In this paper, we investigate the use of deep residual neural to solve the problem of detecting the artistic style of a painting and outperform existing approaches to reach an accuracy of 62 on the Wikipaintings dataset (for 25 different style). To achieve this result, the network is first pre-trained on ImageNet, and deeply retrained for artistic style. We empirically evaluate that to achieve the best performance, one need to retrain about 20 layers. This suggests that the two tasks are as similar as expected, and explain the previous success of hand crafted features. We also demonstrate that the style detected on the Wikipaintings dataset are consistent with styles detected on an independent dataset and describe a number of experiments we conducted to validate this approach both qualitatively and quantitatively.Subjects / Keywords
Art style recognition; Painting; Feature extraction; Deep learningRelated items
Showing items related by title and author.
-
Boria, Nicolas; Negrevergne, Benjamin; Yger, Florian (2020) Communication / Conférence
-
Araújo, Alexandre; Negrevergne, Benjamin; Chevaleyre, Yann; Atif, Jamal (2018) Communication / Conférence
-
Araújo, Alexandre; Negrevergne, Benjamin; Chevaleyre, Yann; Atif, Jamal (2019) Document de travail / Working paper
-
Nguyen, Thanh Hai; Prifti, Edi; Chevaleyre, Yann; Sokolovska, Nataliya; Zucker, Jean-Daniel (2018) Communication / Conférence
-
Cazenave, Tristan; Negrevergne, Benjamin; Sikora, Florian (2020) Communication / Conférence