no code implementations • 23 Apr 2024 • Ronan Sicre, Hanwei Zhang, Julien Dejasmin, Chiheb Daaloul, Stéphane Ayache, Thierry Artières
This paper presents Discriminative Part Network (DP-Net), a deep architecture with strong interpretation capabilities, which exploits a pretrained Convolutional Neural Network (CNN) combined with a part-based recognition module.
no code implementations • 4 May 2021 • Chiheb Daaloul, Thibaut Le Gouic, Jacques Liandrat, Magali Tournus
Our method is based on the gradient flow of the multimarginal formulation of the Wasserstein barycenter, with an additive penalization to account for the marginal constraints.