activity
20122024
most citedGradient-based deterministic inversion of geophysical data with Generative Adversarial Networks: is it feasible?

72 citations · 191 across the 22 of their papers we have counts for

collaborators
Showing 2020Show all

7 papers · 1 filter

cs.LG2020

Open Set Domain Adaptation using Optimal Transport

Marwa Kechaou, Romain Hérault, Mokhtar Z. Alaya +1

We present a 2-step optimal transport approach that performs a mapping from a source distribution to a target distribution. Here, the target has the particularity to present new cl…

cs.LG2020

Optimal Transport for Conditional Domain Matching and Label Shift

Alain Rakotomamonjy, Rémi Flamary, Gilles Gasso +3

We address the problem of unsupervised domain adaptation under the setting of generalized target shift (joint class-conditional and label shifts). For this framework, we theoretica…

cs.CV2020

Object Detection in the DCT Domain: is Luminance the Solution?

Benjamin Deguerre, Clement Chatelain, Gilles Gasso

Object detection in images has reached unprecedented performances. The state-of-the-art methods rely on deep architectures that extract salient features and predict bounding boxes…

eess.AS2020

Foreground-Background Ambient Sound Scene Separation

Michel Olvera, Emmanuel Vincent, Romain Serizel +1

Ambient sound scenes typically comprise multiple short events occurring on top of a somewhat stationary background. We consider the task of separating these events from the backgro…

eess.IV2020★ 10 cited

Pixel-wise Conditioned Generative Adversarial Networks for Image Synthesis and Completion

Cyprien Ruffino, Romain Hérault, Eric Laloy +1

Generative Adversarial Networks (GANs) have proven successful for unsupervised image generation. Several works have extended GANs to image inpainting by conditioning the generation…

stat.ML2020

Theoretical Guarantees for Bridging Metric Measure Embedding and Optimal Transport

Mokhtar Z. Alaya, Maxime Bérar, Gilles Gasso +1

We propose a novel approach for comparing distributions whose supports do not necessarily lie on the same metric space. Unlike Gromov-Wasserstein (GW) distance which compares pairw…