no code implementations • 14 Oct 2023 • Hugo Waltsburger, Erwan Libessart, Chengfang Ren, Anthony Kolar, Regis Guinvarc'h
One of the main applications and novelties is the measurement of algorithmic power efficiency.
1 code implementation • 16 Feb 2023 • Jose Agustin Barrachina, Chengfang Ren, Gilles Vieillard, Christele Morisseau, Jean-Philippe Ovarlez
This work explains in detail the theory behind Complex-Valued Neural Network (CVNN), including Wirtinger calculus, complex backpropagation, and basic modules such as complex layers, complex activation functions, or complex weight initialization.
1 code implementation • 28 Oct 2022 • José Agustin Barrachina, Chengfang Ren, Christèle Morisseau, Gilles Vieillard, Jean-Philippe Ovarlez
In this paper, we investigated the semantic segmentation of Polarimetric Synthetic Aperture Radar (PolSAR) using Complex-Valued Neural Network (CVNN).
no code implementations • 28 Oct 2022 • Max Muzeau, Chengfang Ren, Sébastien Angelliaume, Mihai Datcu, Jean-Philippe Ovarlez
Experiments are performed to show the advantages of our method compared to the conventional Reed-Xiaoli algorithm, highlighting the importance of an efficient despeckling pre-processing step.
1 code implementation • 7 Sep 2022 • Antoine Collas, Arnaud Breloy, Chengfang Ren, Guillaume Ginolhac, Jean-Philippe Ovarlez
The proposed Riemannian gradient descent algorithm is leveraged to solve this second minimization problem.
1 code implementation • 23 Feb 2022 • Antoine Collas, Arnaud Breloy, Guillaume Ginolhac, Chengfang Ren, Jean-Philippe Ovarlez
This paper proposes new algorithms for the metric learning problem.