Paper-Conference

Bridging Arbitrary and Tree Metrics via Differentiable Gromov Hyperbolicity
Pierre Houédry, Nicolas Courty, Florestan Martin-Baillon, Laetitia Chapel, Titouan Vayer
Cite URL
Improving Multimodal Distillation for 3D Semantic Segmentation under Domain Shift
Björn Michele, Alexandre Boulch, Tuan-Hung Vu, Gilles Puy, Renaud Marlet, Nicolas Courty
Cite URL
Domain Adaptation of Time Series through Optimal Transport and Temporal Alignment
Add the full text or supplementary notes for the publication here using Markdown formatting.
François Painblanc, Laëtitia Chapel, Nicolas Courty, Chloé Friguet, Charlotte Pelletier, Romain Tavenard
Cite URL
SALUDA: Surface-based Automotive Lidar Unsupervised Domain Adaptation
Learning models on one labeled dataset that generalize well on another domain is a difficult task, as several shifts might happen …
Bjoern Michele, Alexandre Boulch, Gilles Puy, Tuan-Hung Vu, Renaud Marlet, Nicolas Courty
Cite URL 3DV 2024
SALUDA: Surface-based Automotive Lidar Unsupervised Domain Adaptation
Apprentissage contrastif multi-modal: Du pré-entrainement auto-supervisé à la classification supervisée.
Add the full text or supplementary notes for the publication here using Markdown formatting.
Paul Berg, Minh-Tan Pham, Nicolas Courty
Cite
Domain Adaptation of Time Series through Optimal Transport and Temporal Alignment
Add the full text or supplementary notes for the publication here using Markdown formatting.
François Painblanc, Laëtitia Chapel, Nicolas Courty, Chloé Friguet, Charlotte Pelletier, Romain Tavenard
Cite
Horospherical Learning with Smart Prototypes
Hyperbolic spaces have emerged as an effective manifold to learn representations due to their ability to efficiently represent …
Paul Berg, Björn Michele, Minh-Tan Pham, Laetitia Chapel, Nicolas Courty
Cite BMVC 2024
Horospherical Learning with Smart Prototypes
SALUDA: Surface-based Automotive Lidar Unsupervised Domain Adaptation
Add the full text or supplementary notes for the publication here using Markdown formatting.
Björn Michele, Alexandre Boulch, Gilles Puy, Tuan-Hung Vu, Renaud Marlet, Nicolas Courty
Cite
Train Till You Drop: Towards Stable and Robust Source-free Unsupervised 3D Domain Adaptation
We tackle the challenging problem of source-free unsupervised domain adaptation (SFUDA) for 3D semantic segmentation. It amounts to …
Björn Michele, Alexandre Boulch, Tuan-Hung Vu, Gilles Puy, Renaud Marlet, Nicolas Courty
Cite Code URL ECCV 2024
Train Till You Drop: Towards Stable and Robust Source-free Unsupervised 3D Domain Adaptation
Fast Optimal Transport through Sliced Wasserstein Generalized Geodesics
Add the full text or supplementary notes for the publication here using Markdown formatting.
Guillaume Mahey, Laetitia Chapel, Gilles Gasso, Clément Bonet, Nicolas Courty
Cite URL