Posts by Collection
gallery
publications
SLACK: Stable Learning of Augmentations with Cold-start and KL regularization
Published in IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR), 2023
Juliette Marrie, Michael Arbel, Diane Larlus, Julien Mairal
SLACK is a method for automatically learning optimal data augmentation policies.
Paper · Project page · Code
On Good Practices for Task-Specific Distillation of Large Pretrained Visual Models
Published in Transactions on Machine Learning Research (TMLR), 2024
Juliette Marrie, Michael Arbel, Julien Mairal, Diane Larlus
This paper delineates good practices for leveraging current large pretrained visual models to train a small model on a specific task.
LUDVIG: Learning-free Uplifting of 2D Visual features to Gaussian Splatting scenes
Published in International Conference on Computer Vision (ICCV), 2025
Juliette Marrie, Romain Menegaux, Michael Arbel, Diane Larlus, Julien Mairal
LUDVIG is an efficient, learning-free approach for transferring 2D visual representations into 3D Gaussian Splatting scenes.
Paper · Project page · Code
PanSt3R: Multi-view Consistent Panoptic Segmentation
Published in International Conference on Computer Vision (ICCV), 2025
Lojze Zust, Yohann Cabon, Juliette Marrie, Leonid Antsfeld, Boris Chidlovskii, Jerome Revaud, Gabriela Csurka
PanSt3R jointly reconstructs 3D geometry and panoptic segmentation from unposed multi-view images in a single forward pass, without camera parameters or test-time optimization.
CASA: Cross-Attention via Self-Attention for Efficient Vision-Language Fusion
Published in arXiv preprint, 2025
Moritz Böhle*, Amélie Royer*, Juliette Marrie*, Edouard Grave, Patrick Pérez *Equal contribution.
CASA is a novel vision-language modeling techniques that build on — and improves — cross-attention for multimodal fusion.
Paper · Project page · Code