Deep Learning

An analysis of the transfer learning of convolutional neural networks for artistic images

Transfer learning from huge natural image datasets, fine-tuning of deep neural networks and the use of the corresponding pre-trained networks have become de facto the core of art analysis applications. Nevertheless, the effects of transfer learning …

Deep Learning for Art History

This PhD project concern the recognition and detection of iconographic elements (object, person etc.) in the artworks. The two main points of this PhD are the identification of important need from the Art History and the use of the Deep Learning methods, especially the transfer learning.

Multiple instance learning on deep features for weakly supervised object detection with extreme domain shifts

Weakly supervised object detection (WSOD) using only image-level annotations has attracted a growing attention over the past few years. Whereas such task is typically addressed with a domain-specific solution focused on natural images, we show that a …

Weakly Supervised Object Detection in Artworks

We propose a method for the weakly supervised detection of objects in paintings. At training time, only image-level annotations are needed. This, combined with the efficiency of our multiple-instance learning method, enables one to learn new classes …

Texture Synthesis with Deep Learning

Project on the statistics of the features maps of the Neural Networks used for texture synthesis. This project is based on the Gatys and al. algorithm.