2019_programme: ON THE BENEFIT OF MULTIPLE REPRESENTATIONS WITH CONVOLUTIONAL NEURAL NETWORKS FOR IMPROVED TARGET CLASSIFICATION USING SONAR DATA

Back


  • Session: 04. Towards Automatic Target Recognition. Detection, Classification and Modelling
    Organiser(s): Groen Johannes, Jans Wolfgang, Pailhas Yan, Myers Vincent
  • Lecture: ON THE BENEFIT OF MULTIPLE REPRESENTATIONS WITH CONVOLUTIONAL NEURAL NETWORKS FOR IMPROVED TARGET CLASSIFICATION USING SONAR DATA
    Paper ID: 857
    Author(s): Williams David, Hamon Ronan, Gerg Isaac
    Presenter: Williams David
    Presentation type: oral
    Abstract: The benefit of using multiple representations of data in the context of convolutional neural networks (CNNs) is demonstrated. We present three variations on this theme of multiple representations, in the form of (i) fundamentally different input data representations obtained from the same raw data, (ii) isometries of a given data representation, and (iii) intermediate representations arising from unique CNN architectures. Taken together, these variants can produce excellent classification performance while relying on orders of magnitude fewer free parameters than used in typical CNNs, thereby reducing training data requirements. The value of this multi-representation approach is demonstrated on a target classification task using real, measured sonar data collected at sea.
      Download the full paper
  • Corresponding author: Dr Williams David
    Affiliation: NATO STO CMRE
    Country: Italy
    e-mail:

Back