Détail de l'auteur
Auteur Mathias Ortner |
Documents disponibles écrits par cet auteur (1)
Ajouter le résultat dans votre panier Affiner la recherche Interroger des sources externes
Learning disentangled representations of satellite image time series in a weakly supervised manner / Eduardo Hugo Sanchez (2021)
Titre : Learning disentangled representations of satellite image time series in a weakly supervised manner Type de document : Thèse/HDR Auteurs : Eduardo Hugo Sanchez, Auteur ; Mathieu Serrurier, Directeur de thèse ; Mathias Ortner, Directeur de thèse Editeur : Toulouse : Université de Toulouse 3 Paul Sabatier Année de publication : 2021 Importance : 176 p. Format : 21 x 30 cm Note générale : bibliographie
Thèse en vue de l'obtention du Doctorat de l'Université de Toulouse, Spécialité Informatique et TélécommunicationsLangues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] analyse des mélanges spectraux
[Termes IGN] analyse des mélanges temporels
[Termes IGN] apprentissage automatique
[Termes IGN] classification dirigée
[Termes IGN] classification non dirigée
[Termes IGN] image Sentinel-MSI
[Termes IGN] réseau antagoniste génératif
[Termes IGN] segmentation d'image
[Termes IGN] série temporelleIndex. décimale : THESE Thèses et HDR Résumé : (auteur) This work focuses on learning data representations of satellite image time series via an unsupervised learning approach. The main goal is to enforce the data representation to capture the relevant information from the time series to perform other applications of satellite imagery. However, extracting information from satellite data involves many challenges since models need to deal with massive amounts of images provided by Earth observation satellites. Additionally, it is impossible for human operators to label such amount of images manually for each individual task (e.g. classification, segmentation, change detection, etc.). Therefore, we cannot use the supervised learning framework which achieves state-of-the-art results in many tasks.To address this problem, unsupervised learning algorithms have been proposed to learn the data structure instead of performing a specific task. Unsupervised learning is a powerful approach since no labels are required during training and the knowledge acquired can be transferred to other tasks enabling faster learning with few labels.In this work, we investigate the problem of learning disentangled representations of satellite image time series where a shared representation captures the spatial information across the images of the time series and an exclusive representation captures the temporal information which is specific to each image. We present the benefits of disentangling the spatio-temporal information of time series, e.g. the spatial information is useful to perform time-invariant image classification or segmentation while the knowledge about the temporal information is useful for change detection. To accomplish this, we analyze some of the most prevalent unsupervised learning models such as the variational autoencoder (VAE) and the generative adversarial networks (GANs) as well as the extensions of these models to perform representation disentanglement. Encouraged by the successful results achieved by generative and reconstructive models, we propose a novel framework to learn spatio-temporal representations of satellite data. We prove that the learned disentangled representations can be used to perform several computer vision tasks such as classification, segmentation, information retrieval and change detection outperforming other state-of-the-art models. Nevertheless, our experiments suggest that generative and reconstructive models present some drawbacks related to the dimensionality of the data representation, architecture complexity and the lack of disentanglement guarantees. In order to overcome these limitations, we explore a recent method based on mutual information estimation and maximization for representation learning without relying on image reconstruction or image generation. We propose a new model that extends the mutual information maximization principle to disentangle the representation domain into two parts. In addition to the experiments performed on satellite data, we show that our model is able to deal with different kinds of datasets outperforming the state-of-the-art methods based on GANs and VAEs. Furthermore, we show that our mutual information based model is less computationally demanding yet more effective. Finally, we show that our model is useful to create a data representation that only captures the class information between two images belonging to the same category. Disentangling the class or category of an image from other factors of variation provides a powerful tool to compute the similarity between pixels and perform image segmentation in a weakly-supervised manner. Note de contenu : Introduction
1- Background
2- Representation disentanglement via VAEs/GANs
3- Representation disentanglement via mutual information estimation
ConclusionNuméro de notice : 24065 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Thèse française Note de thèse : Thèse de Doctorat : Informatique et Télécommunications : Toulouse 3 : 2021 Organisme de stage : nstitut de Recherche en Informatique de Toulouse IRIT DOI : sans En ligne : http://thesesups.ups-tlse.fr/4971/1/2021TOU30032.pdf Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=101822