PhD Defense
Date:
PhD Defense from Télécom Paris - Université Paris Saclay with the following commite :
- Agnès Desolneux, CNRS, ENS Paris-Saclay, France
- Mathieu Aubry , ENPC, France
- Javier Portilla, CSIC, Espagne
- Thomas Hurtut, Polytechnique Montréal, Canada
- Sabine Süsstrunk, EPFL, Suisse
- Yann Gousseau, Télécom Paris, France
- Saïd Ladjal, Télécom Paris, France
- Olivier Bonfait, Université de Bourgogne, France
Abstract : In this thesis, we study the transfer of Convolutional Neural Networks (CNN) trained on natural images to related tasks. We follow two axes: texture synthesis and visual recognition in artworks. The first one consists in synthesizing a new image given a reference sample. Most methods are based on enforcing the Gram matrices of ImageNet-trained CNN features. We develop a multi-resolution strategy to take into account large scale structures. This strategy can be coupled with long-range constraints either through a Fourier frequency constraint, or the use of feature maps autocorrelation. This scheme allows excellent high-resolution synthesis especially for regular textures. We compare our methods to alternatives ones with quantitative and perceptual evaluations. In a second axis, we focus on transfer learning of CNN for artistic image classification. CNNs can be used as off-the-shelf feature extractors or fine-tuned. We illustrate the advantage of the last solution. Second, we use feature visualization techniques, CNNs similarity indexes and quantitative metrics to highlight some characteristics of the fine-tuning process. Another possibility is to transfer a CNN trained for object detection. We propose a simple multiple instance method using off-the-shelf deep features and box proposals, for weakly supervised object detection. At training time, only image-level annotations are needed. We experimentally show the interest of our models on six non-photorealistic.
Manuscript - [Slides]((http://ngonthier.github.io/files/PhD_Presentation.pdf)