Descripteur
Termes IGN > informatique > intelligence artificielle > apprentissage automatique > apprentissage non-dirigé
apprentissage non-dirigéVoir aussi |
Documents disponibles dans cette catégorie (65)
Ajouter le résultat dans votre panier
Visionner les documents numériques
Affiner la recherche Interroger des sources externes
Etendre la recherche sur niveau(x) vers le bas
Unsupervised-restricted deconvolutional neural network for very high resolution remote-sensing image classification / Yiting Tao in IEEE Transactions on geoscience and remote sensing, vol 55 n° 12 (December 2017)
[article]
Titre : Unsupervised-restricted deconvolutional neural network for very high resolution remote-sensing image classification Type de document : Article/Communication Auteurs : Yiting Tao, Auteur ; Miaozhong Xu, Auteur ; Fan Zhang, Auteur ; Bo Du, Auteur ; Liangpei Zhang, Auteur Année de publication : 2017 Article en page(s) : pp 6805 - 6823 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] apprentissage non-dirigé
[Termes IGN] classification pixellaire
[Termes IGN] déconvolution
[Termes IGN] image Geoeye
[Termes IGN] image Quickbird
[Termes IGN] méthode fondée sur le noyau
[Termes IGN] réseau neuronal convolutifRésumé : (Auteur) As the acquisition of very high resolution (VHR) satellite images becomes easier owing to technological advancements, ever more stringent requirements are being imposed on automatic image interpretation. Moreover, per-pixel classification has become the focus of research interests in this regard. However, the efficient and effective processing and the interpretation of VHR satellite images remain a critical task. Convolutional neural networks (CNNs) have recently been applied to VHR satellite images with considerable success. However, the prevalent CNN models accept input data of fixed sizes and train the classifier using features extracted directly from the convolutional stages or the fully connected layers, which cannot yield pixel-to-pixel classifications. Moreover, training a CNN model requires large amounts of labeled reference data. These are challenging to obtain because per-pixel labeled VHR satellite images are not open access. In this paper, we propose a framework called the unsupervised-restricted deconvolutional neural network (URDNN). It can solve these problems by learning an end-to-end and pixel-to-pixel classification and handling a VHR classification using a fully convolutional network and a small number of labeled pixels. In URDNN, supervised learning is always under the restriction of unsupervised learning, which serves to constrain and aid supervised training in learning more generalized and abstract feature. To some degree, it will try to reduce the problems of overfitting and undertraining, which arise from the scarcity of labeled training data, and to gain better classification results using fewer training samples. It improves the generality of the classification model. We tested the proposed URDNN on images from the Geoeye and Quickbird sensors and obtained satisfactory results with the highest overall accuracy (OA) achieved as 0.977 and 0.989, respectively. Experiments showed that the combined effects of additional kernels and stages may have produced better results, and two-stage URDNN consistently produced a more stable result. We compared URDNN with four methods and found that with a small ratio of selected labeled data items, it yielded the highest and most stable results, whereas the accuracy values of the other methods quickly decreased. For some categories with fewer training pixels, accuracy for categories from other methods was considerably worse than that in URDNN, with the largest difference reaching almost 10%. Hence, the proposed URDNN can successfully handle the VHR image classification using a small number of labeled pixels. Furthermore, it is more effective than state-of-the-art methods. Numéro de notice : A2017-766 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2017.2734697 En ligne : https://doi.org/10.1109/TGRS.2017.2734697 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=88803
in IEEE Transactions on geoscience and remote sensing > vol 55 n° 12 (December 2017) . - pp 6805 - 6823[article]Remote sensing scene classification by unsupervised representation learning / Xiaoqiang Lu in IEEE Transactions on geoscience and remote sensing, vol 55 n° 9 (September 2017)
[article]
Titre : Remote sensing scene classification by unsupervised representation learning Type de document : Article/Communication Auteurs : Xiaoqiang Lu, Auteur ; Xiangtao Zheng, Auteur ; Yuan Yuan, Auteur Année de publication : 2017 Article en page(s) : pp 5148 - 5157 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] apprentissage non-dirigé
[Termes IGN] classification par séparateurs à vaste marge
[Termes IGN] déconvolution
[Termes IGN] image à haute résolution
[Termes IGN] réseau neuronal artificiel
[Termes IGN] scène
[Termes IGN] Sydney (Nouvelle-Galles du Sud)Résumé : (Auteur) With the rapid development of the satellite sensor technology, high spatial resolution remote sensing (HSR) data have attracted extensive attention in military and civilian applications. In order to make full use of these data, remote sensing scene classification becomes an important and necessary precedent task. In this paper, an unsupervised representation learning method is proposed to investigate deconvolution networks for remote sensing scene classification. First, a shallow weighted deconvolution network is utilized to learn a set of feature maps and filters for each image by minimizing the reconstruction error between the input image and the convolution result. The learned feature maps can capture the abundant edge and texture information of high spatial resolution images, which is definitely important for remote sensing images. After that, the spatial pyramid model (SPM) is used to aggregate features at different scales to maintain the spatial layout of HSR image scene. A discriminative representation for HSR image is obtained by combining the proposed weighted deconvolution model and SPM. Finally, the representation vector is input into a support vector machine to finish classification. We apply our method on two challenging HSR image data sets: the UCMerced data set with 21 scene categories and the Sydney data set with seven land-use categories. All the experimental results achieved by the proposed method outperform most state of the arts, which demonstrates the effectiveness of the proposed method. Numéro de notice : A2017-664 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2017.2702596 En ligne : http://dx.doi.org/10.1109/TGRS.2017.2702596 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=87103
in IEEE Transactions on geoscience and remote sensing > vol 55 n° 9 (September 2017) . - pp 5148 - 5157[article]Learning to diversify deep belief networks for hyperspectral image classification / Ping Zhong in IEEE Transactions on geoscience and remote sensing, vol 55 n° 6 (June 2017)
[article]
Titre : Learning to diversify deep belief networks for hyperspectral image classification Type de document : Article/Communication Auteurs : Ping Zhong, Auteur ; Zhiqiang Gong, Auteur ; Shutao Li, Auteur ; Carola-Bibiane Schönlieb, Auteur Année de publication : 2017 Article en page(s) : pp 3516 - 3530 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] apprentissage non-dirigé
[Termes IGN] classification par réseau neuronal
[Termes IGN] image hyperspectrale
[Termes IGN] réseau neuronal convolutif
[Termes IGN] théorie de Dempster-ShaferRésumé : (Auteur) In the literature of remote sensing, deep models with multiple layers have demonstrated their potentials in learning the abstract and invariant features for better representation and classification of hyperspectral images. The usual supervised deep models, such as convolutional neural networks, need a large number of labeled training samples to learn their model parameters. However, the real-world hyperspectral image classification task provides only a limited number of training samples. This paper adopts another popular deep model, i.e., deep belief networks (DBNs), to deal with this problem. The DBNs allow unsupervised pretraining over unlabeled samples at first and then a supervised fine-tuning over labeled samples. But the usual pretraining and fine-tuning method would make many hidden units in the learned DBNs tend to behave very similarly or perform as “dead” (never responding) or “potential over-tolerant” (always responding) latent factors. These results could negatively affect description ability and thus classification performance of DBNs. To further improve DBN’s performance, this paper develops a new diversified DBN through regularizing pretraining and fine-tuning procedures by a diversity promoting prior over latent factors. Moreover, the regularized pretraining and fine-tuning can be efficiently implemented through usual recursive greedy and back-propagation learning framework. The experiments over real-world hyperspectral images demonstrated that the diversity promoting prior in both pretraining and fine-tuning procedure lead to the learned DBNs with more diverse latent factors, which directly make the diversified DBNs obtain much better results than original DBNs and comparable or even better performances compared with other recent hyperspectral image classification methods. Numéro de notice : A2017-478 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2017.2675902 En ligne : http://dx.doi.org/10.1109/TGRS.2017.2675902 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=86403
in IEEE Transactions on geoscience and remote sensing > vol 55 n° 6 (June 2017) . - pp 3516 - 3530[article]
Titre : An Introduction to Machine Learning Type de document : Guide/Manuel Auteurs : Miroslav Kubat, Auteur Mention d'édition : 2ème édition Editeur : Springer International Publishing Année de publication : 2017 ISBN/ISSN/EAN : 978-3-319-63913-0 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Intelligence artificielle
[Termes IGN] algorithme génétique
[Termes IGN] apprentissage non-dirigé
[Termes IGN] apprentissage par renforcement
[Termes IGN] apprentissage profond
[Termes IGN] arbre de décision
[Termes IGN] classificateur
[Termes IGN] classification barycentrique
[Termes IGN] classification bayesienne
[Termes IGN] exploration de données
[Termes IGN] raisonnement inductif
[Termes IGN] réseau neuronal artificiel
[Termes IGN] test de performanceMots-clés libres : Bayesian classifiersboostingcomputational learning theorydecision treesgenetic algorithmslinear and polynomial classifiersnearest neighbor classifierneural networksperformance evaluationreinforcement learningstatistical learningtime-varying classes, imbalanced representationartificial intelligencemachine learningdata miningdeep learningunsupervised learning Résumé : (Auteur) [Introduction] This textbook presents fundamental machine learning concepts in an easy to understand manner by providing practical advice, using straightforward examples, and offering engaging discussions of relevant applications. The main topics include Bayesian classifiers, nearest-neighbor classifiers, linear and polynomial classifiers, decision trees, neural networks, and support vector machines. Later chapters show how to combine these simple tools by way of “boosting,” how to exploit them in more complicated domains, and how to deal with diverse advanced practical issues. One chapter is dedicated to the popular genetic algorithms. This revised edition contains three entirely new chapters on critical topics regarding the pragmatic application of machine learning in industry. The chapters examine multi-label domains, unsupervised learning and its use in deep learning, and logical approaches to induction as well as Inductive Logic Programming. Numerous chapters have been expanded, and the presentation of the material has been enhanced. The book contains many new exercises, numerous solved examples, thought-provoking experiments, and computer assignments for independent work. Numéro de notice : 26276 Affiliation des auteurs : non IGN Thématique : INFORMATIQUE Nature : Manuel DOI : 10.1007/978-3-319-63913-0 En ligne : https://doi.org/10.1007/978-3-319-63913-0 Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=94915
Titre : Artificial neural networks in geospatial analysis Type de document : Chapitre/Contribution Auteurs : Sucharita Gopal, Auteur Editeur : New York, Londres, Hoboken (New Jersey), ... : John Wiley & Sons Année de publication : 2017 Importance : 7 p. Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Analyse spatiale
[Termes IGN] apprentissage dirigé
[Termes IGN] apprentissage non-dirigé
[Termes IGN] apprentissage semi-dirigé
[Termes IGN] carte de Kohonen
[Termes IGN] Perceptron multicouche
[Termes IGN] réseau neuronal artificielRésumé : (Auteur) [introduction] Artificial neural networks (ANN) are computational models inspired by and designed to simulate biological nervous systems that are capable of performing specific information-processing tasks such as data classification and pattern recognition. ANN seeks to replicate the massively parallel nature of a biological neural network. A neural network is a system composed of many simple processing nodes whose function is determined by network structure and connection strengths. Numéro de notice : H2017-023 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE/INFORMATIQUE Nature : Chapître / contribution Date de publication en ligne : 23/02/2016 En ligne : https://doi.org/10.1002/9781118786352.wbieg0322 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=90378 Airborne lidar estimation of aboveground forest biomass in the absence of field inventory / António Ferraz in Remote sensing, vol 8 n° 8 (August 2016)PermalinkRoad vectorisation from high-resolution imagery based on dynamic clustering using particle swarm optimisation / Fateme Ameri in Photogrammetric record, vol 30 n° 152 (December 2015 - February 2016)PermalinkDistinctive 2D and 3D features for automated large-scale scene analysis in urban areas / Martin Weinmann in Computers and graphics, vol 49 (June 2015)PermalinkDetection, segmentation and classification of 3D urban objects using mathematical morphology and supervised learning / Andrès Serna in ISPRS Journal of photogrammetry and remote sensing, vol 93 (July 2014)PermalinkChange detection in high-resolution land use/land cover geodatabases (at object level) / Emilio Domenech (01/04/2014)PermalinkThe largest empty rectangle containing only a query object in Spatial Databases / Gilberto Gutiérrez in Geoinformatica, vol 18 n° 2 (April 2014)PermalinkMultiple-entity based classification of airborne laser scanning data in urban areas / S. Xu in ISPRS Journal of photogrammetry and remote sensing, vol 88 (February 2014)PermalinkComparaison et évaluation de méthodes d'extraction automatique d'objets sur des images optique et radar / Charlotte Benedetto (2013)PermalinkA framework of region-based spatial relations for non-overlapping features and its application in object based image analysis / Y. Liu in ISPRS Journal of photogrammetry and remote sensing, vol 63 n° 4 (July - August 2008)PermalinkAn application of problem and product ontologies for the revision beach nourishments / Daniel van de Vlag in International journal of geographical information science IJGIS, vol 19 n° 10 (november 2005)Permalink