Descripteur
Termes IGN > informatique > intelligence artificielle > apprentissage automatique > apprentissage semi-dirigé
apprentissage semi-dirigé |
Documents disponibles dans cette catégorie (25)
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
Object detection in optical remote sensing images based on weakly supervised learning and high-level feature learning / Junwei Han in IEEE Transactions on geoscience and remote sensing, vol 53 n° 6 (June 2015)
[article]
Titre : Object detection in optical remote sensing images based on weakly supervised learning and high-level feature learning Type de document : Article/Communication Auteurs : Junwei Han, Auteur ; Dingwen Zhang, Auteur ; Gong Cheng, Auteur Année de publication : 2015 Article en page(s) : pp 3325 - 3337 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] apprentissage semi-dirigé
[Termes IGN] détection d'objet
[Termes IGN] estimation bayesienne
[Termes IGN] état de l'art
[Termes IGN] moteur d'inférenceRésumé : (Auteur) The abundant spatial and contextual information provided by the advanced remote sensing technology has facilitated subsequent automatic interpretation of the optical remote sensing images (RSIs). In this paper, a novel and effective geospatial object detection framework is proposed by combining the weakly supervised learning (WSL) and high-level feature learning. First, deep Boltzmann machine is adopted to infer the spatial and structural information encoded in the low-level and middle-level features to effectively describe objects in optical RSIs. Then, a novel WSL approach is presented to object detection where the training sets require only binary labels indicating whether an image contains the target object or not. Based on the learnt high-level features, it jointly integrates saliency, intraclass compactness, and interclass separability in a Bayesian framework to initialize a set of training examples from weakly labeled images and start iterative learning of the object detector. A novel evaluation criterion is also developed to detect model drift and cease the iterative learning. Comprehensive experiments on three optical RSI data sets have demonstrated the efficacy of the proposed approach in benchmarking with several state-of-the-art supervised-learning-based object detection approaches. Numéro de notice : A2015 - 283 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2014.2374218 Date de publication en ligne : 18/12/2014 En ligne : https://doi.org/10.1109/TGRS.2014.2374218 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=76400
in IEEE Transactions on geoscience and remote sensing > vol 53 n° 6 (June 2015) . - pp 3325 - 3337[article]Réservation
Réserver ce documentExemplaires (1)
Code-barres Cote Support Localisation Section Disponibilité 065-2015061 SL Revue Centre de documentation Revues en salle Disponible Complementarity of discriminative classifiers and spectral unmixing techniques for the interpretation of hyperspectral images / Jun Li in IEEE Transactions on geoscience and remote sensing, vol 53 n° 5 (mai 2015)
[article]
Titre : Complementarity of discriminative classifiers and spectral unmixing techniques for the interpretation of hyperspectral images Type de document : Article/Communication Auteurs : Jun Li, Auteur ; Immaculada Dopido, Auteur ; Paolo Gamba, Auteur ; et al., Auteur Année de publication : 2015 Article en page(s) : pp 2899 - 2912 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] analyse discriminante
[Termes IGN] analyse linéaire des mélanges spectraux
[Termes IGN] apprentissage semi-dirigé
[Termes IGN] classification dirigée
[Termes IGN] image hyperspectraleRésumé : (Auteur) Classification and spectral unmixing are two important techniques for hyperspectral data exploitation. Traditionally, these techniques have been exploited independently. In this paper, we propose a new technique that exploits their complementarity. Specifically, we develop a new framework for semisupervised hyperspectral image classification that naturally integrates the information provided by discriminative classification and spectral unmixing. The idea is to assign more confidence to the information provided by discriminative classification for those pixels that can be easily catalogued due to their spectral purity. For those pixels that are more highly mixed in nature, we assign more confidence to the information provided by spectral unmixing. In this case, we use a traditional spectral unmixing chain to produce the abundance fractions of the pure signatures (endmembers) that model the mixture information at a subpixel level. The decision on which source of information is prioritized in the process is taken adaptively, when new unlabeled samples are selected and included in our semisupervised framework. In this regard, the proposed approach can adaptively integrate these two sources of information without the need to establish any weight parameters, thus exploiting the complementarity of classification and unmixing and selecting the most appropriate source of information in each case. In order to test our concept, which has similar computational complexity as traditional semisupervised classification strategies, we have used two different hyperspectral data sets with different characteristics and spatial resolution. In our experiments, we consider two different discriminative classifiers: multinomial logistic regression and probabilistic support vector machine. The obtained results indicate that the proposed approach, which jointly exploits the features provided by classification and spectral unmixing in adaptive fashion, offers an effective solution to improve- classification performance in hyperspectral scenes containing mixed pixels. Numéro de notice : A2015-521 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2014.2366513 En ligne : https://doi.org/10.1109/TGRS.2014.2366513 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=77532
in IEEE Transactions on geoscience and remote sensing > vol 53 n° 5 (mai 2015) . - pp 2899 - 2912[article]Réservation
Réserver ce documentExemplaires (1)
Code-barres Cote Support Localisation Section Disponibilité 065-2015051 RAB Revue Centre de documentation En réserve L003 Disponible Semisupervised hyperspectral classification using task-driven dictionary learning with Laplacian regularization / Zhangyang Wang in IEEE Transactions on geoscience and remote sensing, vol 53 n° 3 (March 2015)
[article]
Titre : Semisupervised hyperspectral classification using task-driven dictionary learning with Laplacian regularization Type de document : Article/Communication Auteurs : Zhangyang Wang, Auteur ; Nasser M. Nasrabadi, Auteur ; Thomas S. Huang, Auteur Année de publication : 2015 Article en page(s) : pp 1161 - 1173 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] apprentissage semi-dirigé
[Termes IGN] classification pixellaire
[Termes IGN] classification semi-dirigée
[Termes IGN] image hyperspectraleRésumé : (Auteur) We present a semisupervised method for single-pixel classification of hyperspectral images. The proposed method is designed to address the special problematic characteristics of hyperspectral images, namely, high dimensionality of hyperspectral pixels, lack of labeled samples, and spatial variability of spectral signatures. To alleviate these problems, the proposed method features the following components. First, being a semisupervised approach, it exploits the wealth of unlabeled samples in the image by evaluating the confidence probability of the predicted labels, for each unlabeled sample. Second, we propose to jointly optimize the classifier parameters and the dictionary atoms by a task-driven formulation, to ensure that the learned features (sparse codes) are optimal for the trained classifier. Finally, it incorporates spatial information through adding a Laplacian smoothness regularization to the output of the classifier, rather than the sparse codes, making the spatial constraint more flexible. The proposed method is compared with a few comparable methods for classification of several popular data sets, and it produces significantly better classification results. Numéro de notice : A2015-129 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2014.2335177 Date de publication en ligne : 30/07/2014 En ligne : https://doi.org/10.1109/TGRS.2014.2335177 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=75792
in IEEE Transactions on geoscience and remote sensing > vol 53 n° 3 (March 2015) . - pp 1161 - 1173[article]Réservation
Réserver ce documentExemplaires (1)
Code-barres Cote Support Localisation Section Disponibilité 065-2015031 RAB Revue Centre de documentation En réserve L003 Disponible Semisupervised self-learning for hyperspectral image classification / Immaculada Dopido in IEEE Transactions on geoscience and remote sensing, vol 51 n° 7 Tome 1 (July 2013)
[article]
Titre : Semisupervised self-learning for hyperspectral image classification Type de document : Article/Communication Auteurs : Immaculada Dopido, Auteur ; Jun Li, Auteur ; Prashanth Reddy Marpu, Auteur ; et al., Auteur Année de publication : 2013 Article en page(s) : pp 4032 - 4044 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] apprentissage semi-dirigé
[Termes IGN] classification par séparateurs à vaste marge
[Termes IGN] classification semi-dirigée
[Termes IGN] image AVIRIS
[Termes IGN] image hyperspectrale
[Termes IGN] image ROSIS
[Termes IGN] régression logistiqueRésumé : (Auteur) Remotely sensed hyperspectral imaging allows for the detailed analysis of the surface of the Earth using advanced imaging instruments which can produce high-dimensional images with hundreds of spectral bands. Supervised hyperspectral image classification is a difficult task due to the unbalance between the high dimensionality of the data and the limited availability of labeled training samples in real analysis scenarios. While the collection of labeled samples is generally difficult, expensive, and time-consuming, unlabeled samples can be generated in a much easier way. This observation has fostered the idea of adopting semisupervised learning techniques in hyperspectral image classification. The main assumption of such techniques is that the new (unlabeled) training samples can be obtained from a (limited) set of available labeled samples without significant effort/cost. In this paper, we develop a new approach for semisupervised learning which adapts available active learning methods (in which a trained expert actively selects unlabeled samples) to a self-learning framework in which the machine learning algorithm itself selects the most useful and informative unlabeled samples for classification purposes. In this way, the labels of the selected pixels are estimated by the classifier itself, with the advantage that no extra cost is required for labeling the selected pixels using this machine-machine framework when compared with traditional machine-human active learning. The proposed approach is illustrated with two different classifiers: multinomial logistic regression and a probabilistic pixelwise support vector machine. Our experimental results with real hyperspectral images collected by the National Aeronautics and Space Administration Jet Propulsion Laboratory's Airborne Visible-Infrared Imaging Spectrometer and the Reflective Optics Spectrographic Imaging System indicate that the use of self-learning represents an effective and promising strategy in the cont- xt of hyperspectral image classification. Numéro de notice : A2013-374 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2012.2228275 En ligne : https://doi.org/10.1109/TGRS.2012.2228275 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=32512
in IEEE Transactions on geoscience and remote sensing > vol 51 n° 7 Tome 1 (July 2013) . - pp 4032 - 4044[article]Réservation
Réserver ce documentExemplaires (1)
Code-barres Cote Support Localisation Section Disponibilité 065-2013071A RAB Revue Centre de documentation En réserve L003 Disponible Semisupervised learning of hyperspectral data with unknown land-cover classes / G. Jun in IEEE Transactions on geoscience and remote sensing, vol 51 n° 1 Tome 1 (January 2013)
[article]
Titre : Semisupervised learning of hyperspectral data with unknown land-cover classes Type de document : Article/Communication Auteurs : G. Jun, Auteur ; J. Ghosh, Auteur Année de publication : 2013 Article en page(s) : pp 273 - 282 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] analyse de groupement
[Termes IGN] apprentissage semi-dirigé
[Termes IGN] Botswana
[Termes IGN] classification bayesienne
[Termes IGN] image hyperspectrale
[Termes IGN] occupation du sol
[Termes IGN] régression
[Termes IGN] réponse spectrale
[Termes IGN] variationRésumé : (Auteur) Both supervised and semisupervised algorithms for hyperspectral data analysis typically assume that all unlabeled data belong to the same set of land-cover classes that is represented by labeled data. This is not true in general, however, since there may be new classes in the unexplored regions within an image or in areas that are geographically near but topographically distinct. This problem is more likely to occur when one attempts to build classifiers that cover wider areas; such classifiers also need to address spatial variations in acquired spectral signatures if they are to be accurate and robust. This paper presents a semisupervised spatially adaptive mixture model (SESSAMM) to identify land covers from hyperspectral images in the presence of previously unknown land-cover classes and spatial variation of spectral responses. SESSAMM uses a nonparametric Bayesian framework to apply spatially adaptive mechanisms to the mixture model with (potentially) infinitely many components. In this method, each component in the mixture has spatially adapted parameters estimated by Gaussian process regression, and spatial correlations between indicator variables are also considered. The proposed SESSAMM algorithm is applied to hyperspectral data from Botswana and from the DC Mall, where some classes are present only in the unlabeled data. SESSAMM successfully differentiates unlabeled instances of previously known classes from unknown classes and provides better results than the standard Dirichlet process mixture model and other alternatives. Numéro de notice : A2013-014 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2012.2198654 En ligne : https://doi.org/10.1109/TGRS.2012.2198654 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=32152
in IEEE Transactions on geoscience and remote sensing > vol 51 n° 1 Tome 1 (January 2013) . - pp 273 - 282[article]Réservation
Réserver ce documentExemplaires (1)
Code-barres Cote Support Localisation Section Disponibilité 065-2013011A RAB Revue Centre de documentation En réserve L003 Disponible A hybrid classification scheme for mining multisource geospatial data / R. Vatsavai in Geoinformatica, vol 15 n° 1 (January 2011)PermalinkPermalinkSemisupervised one-class support vector machine for classification of remote sensing data / Jordi Munoz-Mari in IEEE Transactions on geoscience and remote sensing, vol 48 n° 8 (August 2010)PermalinkUn graphe génératif pour la classification semi-supervisée / P. Gaillard in Ingénierie des systèmes d'information, ISI : Revue des sciences et technologies de l'information, RSTI, vol 15 n° 2 (mars - avril 2010)Permalink7e conférence francophone sur l'apprentissage automatique, CAp 2005, [Plate-forme AFIA], 30 mai - 3 juin 2005, Nice, France / François Denis (2005)Permalink