Blar i forfatter "Khaleghian, Salman"

Viser treff 1-5 av 5

    • AFSD: Adaptive Feature Space Distillation for Distributed Deep Learning 

      Khaleghian, Salman; Ullah, Habib; Johnsen, Einar Broch; Andersen, Anders; Marinoni, Andrea (Journal article; Tidsskriftartikkel; Peer reviewed, 2022-08-08)
      We propose a novel and adaptive feature space distillation method (AFSD) to reduce the communication overhead among distributed computers. The proposed method improves the Codistillation process by supporting longer update interval rates. AFSD performs knowledge distillates across the models infrequently and provides flexibility to the models in terms of exploring diverse variations in the training ...

    • Deep Semisupervised Teacher–Student Model Based on Label Propagation for Sea Ice Classification 

      Khaleghian, Salman; Ullah, Habib; Kræmer, Thomas; Eltoft, Torbjørn; Marinoni, Andrea (Journal article; Tidsskriftartikkel; Peer reviewed, 2021-10-14)
      In this article, we propose a novelteacher–student-based label propagation deep semisupervised learning (TSLP-SSL) method for sea ice classification based on Sentinel-1 synthetic aperture radar data. For sea ice classification, labeling the data precisely is very time consuming and requires expert knowledge. Our method efficiently learns sea ice characteristics from a limited number of labeled samples ...

    • ExtremeEarth meets satellite data from space 

      Hagos, Desta Haileselassie; Kakantousis, Theofilos; Vlassov, Vladimir; Sheikholeslami, Sina; Wang, Tianze; Dowling, Jim; Paris, Claudia; Marinelli, Daniele; Weikmann, Giulio; Bruzzone, Lorenzo; Khaleghian, Salman; Kræmer, Thomas; Eltoft, Torbjørn; Marinoni, Andrea; Pantazi, Despina-Athanasia; Stamoulis, George; Bilidas, Dimitris; Papadakis, George; Mandilaras, George; Koubarakis, Manolis; Troumpoukis, Antonis; Konstantopoulos, Stasinos; Muerth, Markus; Appel, Florian; Fleming, Andrew; Cziferszky, Andreas (Journal article; Tidsskriftartikkel; Peer reviewed, 2021-08-26)
      Bringing together a number of cutting-edge technologies that range from storing extremely large volumes of data all the way to developing scalable machine learning and deep learning algorithms in a distributed manner and having them operate over the same infrastructure poses unprecedented challenges. One of these challenges is the integration of European Space Agency (ESA)’s Thematic Exploitation ...

    • Scalable computing for earth observation - Application on Sea Ice analysis 

      Khaleghian, Salman (Doctoral thesis; Doktorgradsavhandling, 2022-12-15)
      <p>In recent years, Deep learning (DL) networks have shown considerable improvements and have become a preferred methodology in many different applications. These networks have outperformed other classical techniques, particularly in large data settings. In earth observation from the satellite field, for example, DL algorithms have demonstrated the ability to learn complicated nonlinear relationships ...

    • Sea Ice Classification of SAR Imagery Based on Convolution Neural Networks 

      Khaleghian, Salman; Ullah, Habib; Kræmer, Thomas; Hughes, Nick; Eltoft, Torbjørn; Marinoni, Andrea (Journal article; Tidsskriftartikkel; Peer reviewed, 2021-04-29)
      We explore new and existing convolutional neural network (CNN) architectures for sea ice classification using Sentinel-1 (S1) synthetic aperture radar (SAR) data by investigating two key challenges: binary sea ice versus open-water classification, and a multi-class sea ice type classification. The analysis of sea ice in SAR images is challenging because of the thermal noise effects and ambiguities ...