• openAccess   A New Deep Generative Network for Unsupervised Remote Sensing Single-Image Super-Resolution 

      Haut, Juan M.; Fernandez-Beltran, Ruben; Paoletti, Mercedes Eugenia; Plaza, Javier; Plaza, Antonio; Pla, Filiberto IEEE (2018-11)
      Super-resolution (SR) brings an excellent opportunity to improve a wide range of different remote sensing applications. SR techniques are concerned about increasing the image resolution while providing finer spatial details ...
    • openAccess   Capsule Networks for Hyperspectral Image Classification 

      Paoletti, Mercedes Eugenia; Haut, Juan M.; Fernandez-Beltran, Ruben; Plaza, Javier; Plaza, Antonio; Li, Jun; Pla, Filiberto IEEE (2018-10)
      Convolutional neural networks (CNNs) have recently exhibited an excellent performance in hyperspectral image classification tasks. However, the straightforward CNN-based network architecture still finds obstacles when ...
    • openAccess   Deep Pyramidal Residual Networks for Spectral-Spatial Hyperspectral Image Classification 

      Paoletti, Mercedes Eugenia; Haut, Juan M.; Fernandez-Beltran, Ruben; Plaza, Javier; Plaza, Antonio; Pla, Filiberto IEEE (2018-08)
      Convolutional neural networks (CNNs) exhibit good performance in image processing tasks, pointing themselves as the current state-of-the-art of deep learning methods. However, the intrinsic complexity of remotely sensed ...
    • openAccess   Hyperspectral Unmixing Based on Dual-Depth Sparse Probabilistic Latent Semantic Analysis 

      Fernandez-Beltran, Ruben; Plaza, Antonio; Plaza, Javier; Pla, Filiberto IEEE (2018-06)
      This paper presents a novel approach for spectral unmixing of remotely sensed hyperspectral data. It exploits probabilistic latent topics in order to take advantage of the semantics pervading the latent topic space when ...
    • openAccess   Low-High-Power Consumption Architectures for Deep-Learning Models Applied to Hyperspectral Image Classification 

      Haut, Juan M.; Bernabé, Sergio; Paoletti, Mercedes Eugenia; Fernandez-Beltran, Ruben; Plaza, Antonio; Plaza, Javier IEEE (2018-11)
      Convolutional neural networks have emerged as an excellent tool for remotely sensed hyperspectral image (HSI) classification. Nonetheless, the high computational complexity and energy requirements of these models typically ...
    • openAccess   Multimodal Probabilistic Latent Semantic Analysis for Sentinel-1 and Sentinel-2 Image Fusion 

      Fernandez-Beltran, Ruben; Haut, Juan M.; Paoletti, Mercedes Eugenia; Plaza, Javier; Plaza, Antonio; Pla, Filiberto IEEE (2018-09)
      Probabilistic topic models have recently shown a great potential in the remote sensing image fusion field, which is particularly helpful in land-cover categorization tasks. This letter first studies the application of ...
    • closedAccess   Remote Sensing Image Fusion Using Hierarchical Multimodal Probabilistic Latent Semantic Analysis 

      Fernandez-Beltran, Ruben; Haut, Juan M.; Paoletti, Mercedes Eugenia; Plaza, Javier; Plaza, Antonio; Pla, Filiberto IEEE (2018-11)
      The generative semantic nature of probabilistic topic models has recently shown encouraging results within the remote sensing image fusion field when conducting land cover categorization. However, standard topic models ...
    • openAccess   Remote Sensing Image Superresolution Using Deep Residual Channel Attention 

      Haut, Juan M.; Fernandez-Beltran, Ruben; Paoletti, Mercedes Eugenia; Plaza, Javier; Plaza, Antonio IEEE (2019-07-23)
      The current trend in remote sensing image superresolution (SR) is to use supervised deep learning models to effectively enhance the spatial resolution of airborne and satellite-based optical imagery. Nonetheless, the ...
    • openAccess   Remote Sensing Single-Image Superresolution Based on a Deep Compendium Model 

      Haut, Juan M.; Paoletti, Mercedes Eugenia; Fernandez-Beltran, Ruben; Plaza, Javier; Plaza, Antonio; Li, Jun IEEE (2019-03)
      This letter introduces a novel remote sensing single-image superresolution (SR) architecture based on a deep efficient compendium model. The current deep learning-based SR trend stands for using deeper networks to improve ...