Descripteur
Termes IGN > informatique > intelligence artificielle > apprentissage automatique > apprentissage non-dirigé > réseau antagoniste génératif
réseau antagoniste génératif |
Documents disponibles dans cette catégorie (30)
Ajouter le résultat dans votre panier Affiner la recherche Interroger des sources externes
Etendre la recherche sur niveau(x) vers le bas
Building footprint extraction in Yangon city from monocular optical satellite image using deep learning / Hein Thura Aung in Geocarto international, vol 37 n° 3 ([01/02/2022])
[article]
Titre : Building footprint extraction in Yangon city from monocular optical satellite image using deep learning Type de document : Article/Communication Auteurs : Hein Thura Aung, Auteur ; Sao Hone Pha, Auteur ; Wataru Takeuchi, Auteur Année de publication : 2022 Article en page(s) : pp 792 - 812 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] apprentissage profond
[Termes IGN] Birmanie
[Termes IGN] détection du bâti
[Termes IGN] empreinte
[Termes IGN] image Geoeye
[Termes IGN] image isolée
[Termes IGN] réseau antagoniste génératif
[Termes IGN] vision monoculaireRésumé : (auteur) In this research, building footprints in Yangon City, Myanmar are extracted only from monocular optical satellite image by using conditional generative adversarial network (CGAN). Both training dataset and validating dataset are created from GeoEYE image of Dagon Township in Yangon City. Eight training models are created according to the change of values in three training parameters; learning rate, β1 term of Adam, and number of filters in the first convolution layer of the generator and the discriminator. The images of the validating dataset are divided into four image groups; trees, buildings, mixed trees and buildings, and pagodas. The output images of eight trained models are transformed to the vector images and then evaluated by comparing with manually digitized polygons using completeness, correctness and F1 measure. According to the results, by using CGAN, building footprints can be extracted up to 71% of completeness, 81% of correctness and 69% of F1 score from only monocular optical satellite image. Numéro de notice : A2022-345 Affiliation des auteurs : non IGN Thématique : IMAGERIE/INFORMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/10106049.2020.1740949 Date de publication en ligne : 20/03/2020 En ligne : https://doi.org/10.1080/10106049.2020.1740949 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100526
in Geocarto international > vol 37 n° 3 [01/02/2022] . - pp 792 - 812[article]Siamese Adversarial Network for image classification of heavy mineral grains / Huizhen Hao in Computers & geosciences, vol 159 (February 2022)
[article]
Titre : Siamese Adversarial Network for image classification of heavy mineral grains Type de document : Article/Communication Auteurs : Huizhen Hao, Auteur ; Zhiwei Jiang, Auteur ; Shiping Ge, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : n° 105016 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image
[Termes IGN] apprentissage profond
[Termes IGN] classification barycentrique
[Termes IGN] classification et arbre de régression
[Termes IGN] classification par forêts d'arbres décisionnels
[Termes IGN] extraction de traits caractéristiques
[Termes IGN] microscope électronique
[Termes IGN] minéral
[Termes IGN] polarisation croisée
[Termes IGN] réseau antagoniste génératif
[Termes IGN] réseau neuronal siamois
[Termes IGN] séparateur à vaste margeRésumé : (auteur) The identification of heavy mineral grains based on microscopic images can significantly reduce the time and economic cost of the identification. There are several deep learning models to realize end-to-end identification of mineral image recently. However, due to the variety and complexity of mineral images, the existing models are difficult to accurately recognize heavy mineral grains in microscopic images. Here we propose the Siamese Adversarial Network (SAN) for image classification of the heavy mineral grains, which is the first time to focus on addressing the domain difference of heavy mineral images from different basins. In more details, we design a Siamese feature encoder to extract features of both the plane-polarized and cross-polarized images as internal representation of heavy mineral grains. The features are reconstructed to discard domain-related information by adversarial training the heavy mineral classifier and domain discriminator. The identification performance of the models under the three mixed domain experiments is consistently higher than the performance under the same domain settings respectively which shows that the model we proposed achieves a great generalization ability on unseen domains. Numéro de notice : A2022-174 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1016/j.cageo.2021.105016 Date de publication en ligne : 03/12/2021 En ligne : https://doi.org/10.1016/j.cageo.2021.105016 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=99810
in Computers & geosciences > vol 159 (February 2022) . - n° 105016[article]Apprentissage de représentations et modèles génératifs profonds dans les systèmes dynamiques / Jean-Yves Franceschi (2022)
Titre : Apprentissage de représentations et modèles génératifs profonds dans les systèmes dynamiques Type de document : Thèse/HDR Auteurs : Jean-Yves Franceschi, Auteur ; Sylvain Lamprier, Directeur de thèse ; Patrick Gallinari, Directeur de thèse Editeur : Paris : Sorbonne Université Année de publication : 2022 Importance : 304 p. Format : 21 x 30 cm Note générale : Bibliographie
Thèse soutenue pour obtenir le grade de Docteur en Informatique de Sorbonne UniversitéLangues : Anglais (eng) Descripteur : [Vedettes matières IGN] Intelligence artificielle
[Termes IGN] apprentissage profond
[Termes IGN] classification non dirigée
[Termes IGN] données spatiotemporelles
[Termes IGN] équation différentielle
[Termes IGN] processus stochastique
[Termes IGN] réseau antagoniste génératif
[Termes IGN] réseau neuronal récurrent
[Termes IGN] série temporelle
[Termes IGN] système dynamiqueIndex. décimale : THESE Thèses et HDR Résumé : (auteur) L'essor de l'apprentissage profond trouve notamment sa source dans les avancées scientifiques qu'il a permises en termes d'apprentissage de représentations et de modèles génératifs. Dans leur grande majorité, ces progrès ont cependant été obtenus sur des données textuelles et visuelles statiques, les données temporelles demeurant un défi pour ces méthodes. Compte tenu de leur importance pour l'automatisation croissante de multiples tâches, de plus en plus de travaux en apprentissage automatique s'intéressent aux problématiques d'évolution temporelle. Dans cette thèse, nous étudions ainsi plusieurs aspects de la temporalité et des systèmes dynamiques dans les réseaux de neurones profonds pour l'apprentissage non supervisé de représentations et de modèles génératifs. Premièrement, nous présentons une méthode générale d'apprentissage de représentations non supervisée pour les séries temporelles prenant en compte des besoins pratiques d'efficacité et de flexibilité. Dans un second temps, nous nous intéressons à l'apprentissage pour les séquences structurées de nature spatio-temporelle, couvrant les vidéos et phénomènes physiques. En les modélisant par des équations différentielles paramétrisées par des réseaux de neurones, nous montrons la corrélation entre la découverte de représentations pertinentes d'un côté, et de l'autre la fabrique de modèles prédictifs performants sur ces données. Enfin, nous analysons plus généralement dans une troisième partie les populaires réseaux antagonistes génératifs dont nous décrivons la dynamique d'apprentissage par des équations différentielles, nous permettant d'améliorer la compréhension de leur fonctionnement. Note de contenu : 1- Motivation
2- Time series representation learning
3- State-space predictive models for spatiotemporal data
4- Analysis of GANs’ training dynamics
5- ConclusionNuméro de notice : 15203 Affiliation des auteurs : non IGN Thématique : INFORMATIQUE Nature : Thèse française Note de thèse : Thèse de Doctorat : Informatique : Paris : 2022 DOI : sans En ligne : https://tel.hal.science/tel-03591720 Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100472 Contribution to object extraction in cartography : A novel deep learning-based solution to recognise, segment and post-process the road transport network as a continuous geospatial element in high-resolution aerial orthoimagery / Calimanut-Ionut Cira (2022)
Titre : Contribution to object extraction in cartography : A novel deep learning-based solution to recognise, segment and post-process the road transport network as a continuous geospatial element in high-resolution aerial orthoimagery Type de document : Thèse/HDR Auteurs : Calimanut-Ionut Cira, Auteur Editeur : Madrid [Espagne] : Universidad politécnica de Madrid Année de publication : 2022 Importance : 227 p. Format : 21 x 30 cm Note générale : bibliographie
Thèse de Doctorat en Topographie, Géodésie et cartographie, Universidad politécnica de MadridLangues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] analyse d'image orientée objet
[Termes IGN] classification par réseau neuronal convolutif
[Termes IGN] extraction du réseau routier
[Termes IGN] image aérienne
[Termes IGN] orthoimage
[Termes IGN] réseau antagoniste génératif
[Termes IGN] réseau neuronal artificiel
[Termes IGN] route
[Termes IGN] segmentation sémantiqueIndex. décimale : THESE Thèses et HDR Résumé : (auteur) Remote sensing imagery combined with deep learning strategies is often regarded as an ideal solution for interpreting scenes and monitoring infrastructures with remarkable performance levels. Remote sensing experts have been actively using deep neural networks to solve object extraction tasks in high-resolution aerial imagery by means of supervised operations. However, the extraction operation is imperfect, due to the nature of remotely sensed images (noise, obstructions, etc.), the limitations of sensing resolution, or the occlusions often present in the scenes. The road network plays an important part in transportation and, nowadays, one of the main related challenges is keeping the existent cartographic support up to date. This task can be considered very challenging due to the complex nature of the geospatial object (continuous, with irregular geometry, and significant differences in width). We also need to take into account that secondary roads represent the largest part of the road transport network, but due to the absence of clearly defined edges, and the different spectral signatures of the materials used for pavement, monitoring, and mapping them represents a great effort for public administration, and their extraction is often omitted altogether. We believe that recent advancements in machine vision can enable a successful extraction of the road structures from high-resolution, remotely sensed imagery and a greater automation of the road mapping operation. In this PhD thesis, we leverage recent computer vision advances and propose a deep learning-based end-to-end solution, capable of efficiently extracting the surface area of roads at a large scale. The novel approach is based on a disjoint execution of three different image processing operations (recognition, semantic segmentation, and post-processing with conditional generative learning) within a common framework. We focused on improving the state-of-the-art results for each of the mentioned components, before incorporating the resulting models into the proposed solution architecture. For the recognition operation, we proposed two framework candidates based on convolutional neural networks to classify roads in openly available aerial orthoimages divided in tiles of 256×256 pixels, with a spatial resolution of 0.5 m. The frameworks are based on ensemble learning and transfer learning and combine weak classifiers to leverage the strengths of different state-of-the-art models that we heavily modified for computational efficiency. We evaluated their performance on unseen test data and compared the results with those obtained by the state-of-the-art convolutional neural networks trained for the same task, observing improvements in performance metrics of 2-3%. Secondly, we implemented hybrid semantic segmentation models (where the default backbones are replaced by neural network specialised in image segmentation) and trained them with high-resolution remote sensing imagery and their correspondent ground-truth masks. Our models achieved mean increases in performance metrics of 2.7-3.5%, when compared to the original state-of-the-art semantic segmentation architectures trained from scratch for the same task. The best-performing model was integrated on a web platform that handles the evaluation of large areas, the association of the semantic predictions with geographical coordinates, the conversion of the tiles’ format, and the generation of GeoTIFF results (compatible with geospatial databases). Thirdly, the road surface area extraction task is generally carried out via semantic segmentation over remotely sensed imagery—however, this supervised learning task can be considered very costly because it requires remote sensing images labelled at pixel level and the results are not always satisfactory (presence of discontinuities, overlooked connection points, or isolated road segments). We consider that unsupervised learning (not requiring labelled data) can be employed for post-processing the geometries of geospatial objects extracted via semantic segmentation. For this reason, we also approached the post-processing of the road surface areas obtained with the best performing segmentation model to improve the initial segmentation predictions. In this line, we proposed two post-processing operations based on conditional generative learning for deep inpainting and image-to-image translation operations and trained the networks to learn the distribution of the road network present in official cartography, using a novel dataset covering representative areas of Spain. The first proposed conditional Generative Adversarial Network (cGAN) model was trained for deep inpainting operation and obtained improvements in performance metrics of maximum 1.3%. The second cGAN model was trained for image-to-image translation, is based on a popular model heavily modified for computational efficiency (a 92.4% decrease in the number of parameters in the generator network and a 61.3% decrease in the discriminator network), and achieved a maximum increase of 11.6% in performance metrics. We also conducted a qualitative comparison to visually assess the effectiveness of the generative operations and observed great improvements with respect to the initial semantic segmentation predictions. Lastly, we proposed an end-to-end processing strategy that combines image classification, semantic segmentation, and post-processing operations to extract containing road surface area extraction from high-resolution aerial orthophotography. The training of the model components was carried out on a large-scale dataset containing more than 537,500 tiles, covering approximately 20,800 km2 of the Spanish territory, manually tagged at pixel level. The consecutive execution of the resulting deep learning models delivered higher quality results when compared to state-of-the-art implementations trained for the same task. The versatility and flexibility of the solution given by the disjointed execution of the three separate sub-operations proved its effectiveness and economic efficiency and enables the integration of a web application that alleviates the manipulation of geospatial data, while allowing for an easy integration of future models and algorithms. Resuming, applying the proposed models resulted from this PhD thesis translates to operations aimed to check if the latest existing aerial orthoimages contains the studied continuous geospatial element, to obtain an approximation of its surface area using supervised learning and to improve the initial segmentation results with post-processing methods based on conditional generative learning. The results obtained with the proposed end-to-end-solution presented in this PhD thesis improve the state-of-the-art in the field of road extraction with deep learning techniques and prove the appropriateness of applying the proposed extraction workflow for a more robust and more efficient extraction operation of the road transport network. We strongly believe that the processing strategy can be applied to enhance other similar extraction tasks of continuous geospatial elements (such as the mapping of riverbeds, or railroads), or serve as a base for developing additional extraction workflows of geospatial objects from remote sensing images. Note de contenu : 1- Introduction
2- Methodology
3- Theoretical framework
4- Litterature review
5- Road recognition: A framework based on nestion of convolutional neuronal networks and transfer learning to regognise road elements
6- Road segmentation: An approach based on hybrid semantic segmentation models to extract the surface area of rod elements from aerial orthoimagery
7- Post-processing of semantic segmentation predictions I: A conditional generative adversial network to improve the extraction of road surface areas via deep inpainting operations
8- Post-processing of semantic segmentation predictions II: A lightweight conditional generative adversial network to improve the extraction of road surface areas via image-to-image translation
9- An end-to-end road extraction solution based on regonition, segmentation, and post-processing operations for a large-scale mapping of the road transport network from aerial orthophotography
10- ConclusionsNuméro de notice : 24069 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Thèse étrangère Note de thèse : Thèse de Doctorat : Topographie, Géodésie et cartographie : Universidad politécnica de Madrid : 2022 DOI : 10.20868/UPM.thesis.70152 En ligne : https://doi.org/10.20868/UPM.thesis.70152 Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=102113 Deep image translation with an affinity-based change prior for unsupervised multimodal change detection / Luigi Tommaso Luppino in IEEE Transactions on geoscience and remote sensing, vol 60 n° 1 (January 2022)
[article]
Titre : Deep image translation with an affinity-based change prior for unsupervised multimodal change detection Type de document : Article/Communication Auteurs : Luigi Tommaso Luppino, Auteur ; Michael Kampffmeyer, Auteur ; filipo Maria Bianchi, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : n° 4700422 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image mixte
[Termes IGN] analyse comparative
[Termes IGN] architecture de réseau
[Termes IGN] classification non dirigée
[Termes IGN] classification par réseau neuronal convolutif
[Termes IGN] détection de changement
[Termes IGN] extraction de traits caractéristiques
[Termes IGN] réseau antagoniste génératifRésumé : (auteur) Image translation with convolutional neural networks has recently been used as an approach to multimodal change detection. Existing approaches train the networks by exploiting supervised information of the change areas, which, however, is not always available. A main challenge in the unsupervised problem setting is to avoid that change pixels affect the learning of the translation function. We propose two new network architectures trained with loss functions weighted by priors that reduce the impact of change pixels on the learning objective. The change prior is derived in an unsupervised fashion from relational pixel information captured by domain-specific affinity matrices. Specifically, we use the vertex degrees associated with an absolute affinity difference matrix and demonstrate their utility in combination with cycle consistency and adversarial training. The proposed neural networks are compared with the state-of-the-art algorithms. Experiments conducted on three real data sets show the effectiveness of our methodology. Numéro de notice : A2022-027 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2021.3056196 Date de publication en ligne : 17/02/2021 En ligne : https://doi.org/10.1109/TGRS.2021.3056196 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=99263
in IEEE Transactions on geoscience and remote sensing > vol 60 n° 1 (January 2022) . - n° 4700422[article]PermalinkSelf-attention and generative adversarial networks for algae monitoring / Nhut Hai Huynh in European journal of remote sensing, vol 55 n° 1 (2022)PermalinkUnsupervised generative models for data analysis and explainable artificial intelligence / Mohanad Abukmeil (2022)PermalinkA deep translation (GAN) based change detection network for optical and SAR remote sensing images / Xinghua Li in ISPRS Journal of photogrammetry and remote sensing, vol 179 (September 2021)PermalinkStochastic super-resolution for downscaling time-evolving atmospheric fields with a generative adversarial network / Jussi Leinonen in IEEE Transactions on geoscience and remote sensing, Vol 59 n° 9 (September 2021)PermalinkUnsupervised denoising for satellite imagery using wavelet directional cycleGAN / Shaoyang Kong in IEEE Transactions on geoscience and remote sensing, vol 59 n° 8 (August 2021)PermalinkImproving human mobility identification with trajectory augmentation / Fan Zhou in Geoinformatica, vol 25 n° 3 (July 2021)PermalinkMultisensor data fusion for cloud removal in global and all-season Sentinel-2 imagery / Patrick Ebel in IEEE Transactions on geoscience and remote sensing, Vol 59 n° 7 (July 2021)PermalinkRemote sensing image colorization using symmetrical multi-scale DCGAN in YUV color space / Min Wu in The Visual Computer, vol 37 n° 7 (July 2021)PermalinkSemiCDNet: A semisupervised convolutional neural network for change detection in high resolution remote-sensing images / Daifeng Peng in IEEE Transactions on geoscience and remote sensing, Vol 59 n° 7 (July 2021)Permalink