• xmlui.mirage2.page-structure.header.title
    • français
    • English
  • Help
  • Login
  • Language 
    • Français
    • English
View Item 
  •   BIRD Home
  • LAMSADE (UMR CNRS 7243)
  • LAMSADE : Publications
  • View Item
  •   BIRD Home
  • LAMSADE (UMR CNRS 7243)
  • LAMSADE : Publications
  • View Item
JavaScript is disabled for your browser. Some features of this site may not work without it.

Browse

BIRDResearch centres & CollectionsBy Issue DateAuthorsTitlesTypeThis CollectionBy Issue DateAuthorsTitlesType

My Account

LoginRegister

Statistics

Most Popular ItemsStatistics by CountryMost Popular Authors
Thumbnail

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
lecoutre17a.pdf (1.031Mb)
Type
Communication / Conférence
Date
2017
Conference title
9th Asian Conference on Machine Learning (ACML 2017)
Conference date
2017-11
Conference city
Seoul
Conference country
"Korea
Book title
Proceedings of the 9th Asian Conference on Machine Learning (ACML 2017)
Book author
Noh, Yung-Kyun; Zhang, Min-Ling
Publisher
JMLR: Workshop and Conference Proceedings
Pages
327-342
Metadata
Show full item record
Author(s)
Lecoutre, Adrian
Laboratoire d'analyse et modélisation de systèmes pour l'aide à la décision [LAMSADE]
Negrevergne, Benjamin cc
Laboratoire d'analyse et modélisation de systèmes pour l'aide à la décision [LAMSADE]
Yger, Florian cc
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 learning

Related items

Showing items related by title and author.

  • Thumbnail
    Fréchet Mean Computation in Graph Space through Projected Block Gradient Descent 
    Boria, Nicolas; Negrevergne, Benjamin; Yger, Florian (2020) Communication / Conférence
  • Thumbnail
    Training Compact Deep Learning Models for Video Classification Using Circulant Matrices 
    Araújo, Alexandre; Negrevergne, Benjamin; Chevaleyre, Yann; Atif, Jamal (2018) Communication / Conférence
  • Thumbnail
    On the Expressive Power of Deep Fully Circulant Neural Networks 
    Araújo, Alexandre; Negrevergne, Benjamin; Chevaleyre, Yann; Atif, Jamal (2019) Document de travail / Working paper
  • Thumbnail
    Disease Classification in Metagenomics with 2D Embeddings and Deep Learning 
    Nguyen, Thanh Hai; Prifti, Edi; Chevaleyre, Yann; Sokolovska, Nataliya; Zucker, Jean-Daniel (2018) Communication / Conférence
  • Thumbnail
    Monte Carlo Graph Coloring 
    Cazenave, Tristan; Negrevergne, Benjamin; Sikora, Florian (2020) Communication / Conférence
Dauphine PSL Bibliothèque logo
Place du Maréchal de Lattre de Tassigny 75775 Paris Cedex 16
Phone: 01 44 05 40 94
Contact
Dauphine PSL logoEQUIS logoCreative Commons logo