no code implementations • 6 Feb 2023 • Anderson Santana de Oliveira, Caelin Kaplan, Khawla Mallat, Tanmay Chakraborty
Recent works have shown that selecting an optimal model architecture suited to the differential privacy setting is necessary to achieve the best possible utility for a given privacy budget using differentially private stochastic gradient descent (DP-SGD)(Tramer and Boneh 2020; Cheng et al. 2022).
no code implementations • 11 Apr 2022 • Tanmay Chakraborty, Utkarsh Trehan, Khawla Mallat, Jean-Luc Dugelay
The drawback of this method is that it cannot be used to generalize CNN behaviour.
no code implementations • 6 Sep 2021 • Khawla Mallat, Fabiola Becerra-Riera, Annette Morales-González, Heydi Méndez-Vázquez, Jean-Luc Dugelay
In this paper, we explore whether automatic face recognition can help in verifying widespread misinformation on social media, particularly conspiracy theories that are based on the existence of body doubles.
no code implementations • 9 Jun 2020 • Jin Keong, Xingbo Dong, Zhe Jin, Khawla Mallat, Jean-Luc Dugelay
The experiment conducted on Eurecom's visible and thermal paired database shows the superior performance of DMSL over the state-of-the-art for thermal facial landmark detection.
no code implementations • 21 Oct 2019 • Naser Damer, Fadi Boutros, Khawla Mallat, Florian Kirchbuchner, Jean-Luc Dugelay, Arjan Kuijper
Generating visible-like face images from thermal images is essential to perform manual and automatic cross-spectrum face recognition.