Hubert Leterme

ENSICAEN (GREYC research institute, Image team), CEA Paris-Saclay (Astrophysics Division, CosmoStat team)


Postdoctoral researcher


14000 Caen, France

I am a postdoctoral researcher in astrostatistics at ENSICAEN (Caen, France) and CEA Paris-Saclay (Paris metropolitan area, France), under the supervision of Jalal Fadili (ENSICAEN) and Jean-Luc Starck (CEA). My research is part of the the TOSCA project, focusing on weak lensing statistics for cosmology, which explores the synergies between Euclid and SKAO. My work will contribute to the reconstruction of mass maps from radio shear measurements using deep learning techniques, with a specific emphasis on uncertainty quantification.

I completed my PhD in June 2023 at the University of Grenoble Alpes and Inria (Thoth team), supervised by Valérie Perrier, Karteek Alahari, and Kévin Polisano. My research lied at the intersection between computer vision and image processing, with a focus on convolutional neural networks, wavelets and stochastic signal processing.

Before my PhD, I received an engineering degree (MSc) from CentraleSupelec, University of Paris-Saclay, with a focus on industrial engineering, supply chain management, and operations research. After a few years working in the industry, including a two-year experience in Sweden, I decided to take a 180 degree turn and to embark in the research adventure. This brought me to Grenoble in 2018, where I received a MSc degree in industrial and applied mathematics from the University of Grenoble Alpes and Grenoble INP Institute of Engineering and Management.


Jun 14, 2023 PhD defense. Title: “A Complex Wavelet Approach for Shift-Invariant Convolutional Neural Networks.”
Jul 13, 2022 My personal website is finally released! :smiley:
Jun 29, 2022 Talk at Rutgers University, New Jersey. Video available!
Jun 19, 2022 I am at CVPR 2022, New Orleans, Louisiana, from June 19th to 24th.
May 19, 2022 I am at Kymatio’22 workshop in Nantes, France, where deep learning meets wavelet theory.

Selected Publications

  1. Doctoral Thesis
    A Complex Wavelet Approach for Shift-Invariant Convolutional Neural Networks
    Leterme, Hubert
    Jun 2023
  2. Preprint
    From CNNs to Shift-Invariant Twin Models Based on Complex Wavelets
    Mar 2023
  3. Preprint
    On the Shift Invariance of Max Pooling Feature Maps in Convolutional Neural Networks
    Sep 2022