Skip to Main content Skip to Navigation
Theses

Réseaux de neurones convolutifs pour la segmentation sémantique et l'apprentissage d'invariants de couleur

Abstract : Computer vision is an interdisciplinary field that investigates how computers can gain a high level of understanding from digital images or videos. In artificial intelligence, and more precisely in machine learning, the field in which this thesis is positioned,computer vision involves extracting characteristics from images and then generalizing concepts related to these characteristics. This field of research has become very popular in recent years, particularly thanks to the results of the convolutional neural networks that form the basis of so-called deep learning methods. Today, neural networks make it possible, among other things, to recognize different objects present in an image, to generate very realistic images or even to beat the champions at the Go game. Their performance is not limited to the image domain, since they are also used in other fields such as natural language processing (e. g. machine translation) or sound recognition. In this thesis, we study convolutional neural networks in order to develop specialized architectures and loss functions for low-level tasks (color constancy) as well as high-level tasks (semantic segmentation). Color constancy, is the ability of the human visual system to perceive constant colours for a surface despite changes in the spectrum of illumination (lighting change). In computer vision, the main approach consists in estimating the color of the illuminant and then suppressing its impact on the perceived color of objects. We approach the task of color constancy with the use of neural networks by developing a new architecture composed of a subsampling operator inspired by traditional methods. Our experience shows that our method makes it possible to obtain competitive performances with the state of the art. Nevertheless, our architecture requires a large amount of training data. In order to partially correct this problem and improve the training of neural networks, we present several techniques for artificial data augmentation. We are also making two contributions on a high-level issue : semantic segmentation. This task, which consists of assigning a semantic class to each pixel of an image, is a challenge in computer vision because of its complexity. On the one hand, it requires many examples of training that are costly to obtain. On the other hand, it requires the adaptation of traditional convolutional neural networks in order to obtain a so-called dense prediction, i. e., a prediction for each pixel present in the input image. To solve the difficulty of acquiring training data, we propose an approach that uses several databases annotated with different labels at the same time. To do this, we define a selective loss function that has the advantage of allowing the training of a convolutional neural network from data from multiple databases. We also developed self-context approach that captures the correlations between labels in different databases. Finally, we present our third contribution : a new convolutional neural network architecture called GridNet specialized for semantic segmentation. Unlike traditional networks, implemented with a single path from the input (image) to the output (prediction), our architecture is implemented as a 2D grid allowing several interconnected streams to operate at different resolutions. In order to exploit all the paths of the grid, we propose a technique inspired by dropout. In addition, we empirically demonstrate that our architecture generalize many of well-known stateof- the-art networks. We conclude with an analysis of the empirical results obtained with our architecture which, although trained from scratch, reveals very good performances, exceeding popular approaches often pre-trained
Complete list of metadatas

Cited literature [215 references]  Display  Hide  Download

https://tel.archives-ouvertes.fr/tel-02111472
Contributor : Abes Star :  Contact
Submitted on : Friday, April 26, 2019 - 9:27:31 AM
Last modification on : Monday, January 13, 2020 - 5:46:07 PM

File

These-FOURURE-Damien-2017.pdf
Version validated by the jury (STAR)

Identifiers

  • HAL Id : tel-02111472, version 1

Citation

Damien Fourure. Réseaux de neurones convolutifs pour la segmentation sémantique et l'apprentissage d'invariants de couleur. Vision par ordinateur et reconnaissance de formes [cs.CV]. Université de Lyon, 2017. Français. ⟨NNT : 2017LYSES056⟩. ⟨tel-02111472⟩

Share

Metrics

Record views

491

Files downloads

870