Diane Larlus

papers

1,463

total citations

papers (15)

Continual Adaptation of Visual Representations via Domain Randomization and Meta-Learning

CVPR 2021arXiv

citations

Concept Generalization in Visual Representation Learning

ICCV 2021arXiv

citations

EPIC Fields: Marrying 3D Geometry and Video Understanding

NEURIPS 2023arXiv

citations

Geo4D: Leveraging Video Generators for Geometric 4D Scene Reconstruction

ICCV 2025arXiv

citations

On the Road to Online Adaptation for Semantic Image Segmentation

CVPR 2022arXiv

citations

UNIC: Universal Classification Models via Multi-teacher Distillation

ECCV 2024arXiv

citations

LUDVIG: Learning-Free Uplifting of 2D Visual Features to Gaussian Splatting Scenes

ICCV 2025arXiv

citations

Granularity-Aware Adaptation for Image Retrieval over Multiple Tasks

ECCV 2022arXiv

citations

SLACK: Stable Learning of Augmentations With Cold-Start and KL Regularization

CVPR 2023arXiv

citations

DUNE: Distilling a Universal Encoder from Heterogeneous 2D and 3D Teachers

CVPR 2025

citations

Fake It Till You Make It: Learning Transferable Representations From Synthetic ImageNet Clones

CVPR 2023

citations

Layered Motion Fusion: Lifting Motion Segmentation to 3D in Egocentric Videos

CVPR 2025arXiv

citations

Diane Larlus

papers (15)

Hard Negative Mixing for Contrastive Learning

Probabilistic Embeddings for Cross-Modal Retrieval

Learning Visual Representations with Caption Annotations

Continual Adaptation of Visual Representations via Domain Randomization and Meta-Learning

Concept Generalization in Visual Representation Learning

EPIC Fields: Marrying 3D Geometry and Video Understanding

Geo4D: Leveraging Video Generators for Geometric 4D Scene Reconstruction

On the Road to Online Adaptation for Semantic Image Segmentation

UNIC: Universal Classification Models via Multi-teacher Distillation

LUDVIG: Learning-Free Uplifting of 2D Visual Features to Gaussian Splatting Scenes

Granularity-Aware Adaptation for Image Retrieval over Multiple Tasks

SLACK: Stable Learning of Augmentations With Cold-Start and KL Regularization

DUNE: Distilling a Universal Encoder from Heterogeneous 2D and 3D Teachers

Fake It Till You Make It: Learning Transferable Representations From Synthetic ImageNet Clones

Layered Motion Fusion: Lifting Motion Segmentation to 3D in Egocentric Videos

papers (15)

Hard Negative Mixing for Contrastive Learning

Probabilistic Embeddings for Cross-Modal Retrieval

Learning Visual Representations with Caption Annotations

Continual Adaptation of Visual Representations via Domain Randomization and Meta-Learning

Concept Generalization in Visual Representation Learning

EPIC Fields: Marrying 3D Geometry and Video Understanding

Geo4D: Leveraging Video Generators for Geometric 4D Scene Reconstruction

On the Road to Online Adaptation for Semantic Image Segmentation

UNIC: Universal Classification Models via Multi-teacher Distillation

LUDVIG: Learning-Free Uplifting of 2D Visual Features to Gaussian Splatting Scenes

Granularity-Aware Adaptation for Image Retrieval over Multiple Tasks

SLACK: Stable Learning of Augmentations With Cold-Start and KL Regularization

DUNE: Distilling a Universal Encoder from Heterogeneous 2D and 3D Teachers

Fake It Till You Make It: Learning Transferable Representations From Synthetic ImageNet Clones

Layered Motion Fusion: Lifting Motion Segmentation to 3D in Egocentric Videos