Geometric Deep Learning for Shape Analysis

Decanato - Facoltà di scienze informatiche

Data d'inizio:

Data di fine:

USI Lugano Campus, room SI-003, Informatics building (Via G. Buffi 13)

You are cordially invited to attend the PhD Dissertation Defense of Davide BOSCAINI on Wednesday, August 16th 2017 at 10h30 in room SI-003 (Informatics building)Abstract:The past decade in computer vision research has witnessed the re-emergence of artificial neural networks (ANN), and in particular convolutional neural network (CNN) techniques, allowing to learn powerful feature representations from large collections of data.Nowadays these techniques are better known under the umbrella term "deep learning" and have achieved a breakthrough in performance in a wide range of image analysis applications such as image classification, segmentation, and annotation.Nevertheless, when attempting to apply deep learning paradigms to 3D shapes one has to face fundamental differences between images and geometric objects.The main difference between images and 3D shapes is the non-Euclidean nature of the latter. This implies that basic operations, such as linear combination or convolution, that are taken for granted in the Euclidean case, are not even well defined on non-Euclidean domains.This happens to be the major obstacle that so far has precluded the successful application of deep learning methods on non-Euclidean geometric data.The goal of this thesis is to overcome this obstacle by extending deep learning tecniques (including, but not limiting to CNNs) to non-Euclidean domains.We present different approaches providing such extension and test their effectiveness in the context of shape similarity and correspondence applications.The proposed approaches are evaluated on several challenging experiments, achieving state-of-the-art results significantly outperforming other methods.Dissertation Committee:

  • Michael Bronstein, Università della Svizzera italiana, Switzerland (Research Advisor)
  • Jonatan Masci, NNAISENSE, Switzerland (Research co-Advisor)
  • Kai Hormann, Università della Svizzera italiana, Switzerland (Internal Member)
  • Jürgen Schmidhuber, Università della Svizzera italiana, Switzerland (Internal Member)
  • Pierre Vandergheynst, École polytechnique fédérale de Lausanne, Switzerland (External Member)
  • Maks Ovsjanikov, École Polytechnique, France (External Member)