Centre de documentation
scientifique

Graph convolutional networks by architecture search for PolSAR image classification / Hongying Liu in Remote sensing, vol 13 n° 7 (April-1 2021)  

Public [article]  inRemote sensing > vol 13 n° 7 (April-1 2021) . - n° 1404 Titre : Graph convolutional networks by architecture search for PolSAR image classification Type de document : Article/Communication Auteurs : Hongying Liu, Auteur ; Derong Xu, Auteur ; Tianwen Zhu, Auteur ; et al., Auteur Année de publication : 2021 Article en page(s) : n° 1404 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image radar et applications [Termes IGN] apprentissage profond [Termes IGN] bande L [Termes IGN] classification par nuées dynamiques [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] classification par séparateurs à vaste marge [Termes IGN] classification semi-dirigée [Termes IGN] échantillon [Termes IGN] graphe [Termes IGN] image AIRSAR [Termes IGN] image radar moirée [Termes IGN] noeud [Termes IGN] polarimétrie radar [Termes IGN] réseau neuronal de graphes Résumé : (auteur) Classification of polarimetric synthetic aperture radar (PolSAR) images has achieved good results due to the excellent fitting ability of neural networks with a large number of training samples. However, the performance of most convolutional neural networks (CNNs) degrades dramatically when only a few labeled training samples are available. As one well-known class of semi-supervised learning methods, graph convolutional networks (GCNs) have gained much attention recently to address the classification problem with only a few labeled samples. As the number of layers grows in the network, the parameters dramatically increase. It is challenging to determine an optimal architecture manually. In this paper, we propose a neural architecture search method based GCN (ASGCN) for the classification of PolSAR images. We construct a novel graph whose nodes combines both the physical features and spatial relations between pixels or samples to represent the image. Then we build a new searching space whose components are empirically selected from some graph neural networks for architecture search and develop the differentiable architecture search method to construction our ASGCN. Moreover, to address the training of large-scale images, we present a new weighted mini-batch algorithm to reduce the computing memory consumption and ensure the balance of sample distribution, and also analyze and compare with other similar training strategies. Experiments on several real-world PolSAR datasets show that our method has improved the overall accuracy as much as 3.76% than state-of-the-art methods. Numéro de notice : A2021-350 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.3390/rs13071404 Date de publication en ligne : 06/04/2021 En ligne : https://doi.org/10.3390/rs13071404 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97600 [article]