Oriane Siméoni
Oriane Siméoni has a total of 19 co-authors. Here are the top co-authors by number of shared publications:
- Andrei Bursuc
Valeo.ai
3 shared publications - Patrick Pérez
Valeo.ai
3 shared publications - Antonin Vobecky
VALEO
2 shared publications - David Hurych
Valeo.ai
2 shared publications - Josef Sivic
Czech Institute of Informatics, Robotics and Cybernetics, Czech Technical University in Prague
2 shared publications - Spyros Gidaris
Valeo-ai
2 shared publications
Latest Publications
- 24 November 2024
- Published by Springer Nature
- p. 320-337
CLIP-DINOiser: Teaching CLIP a Few DINO Tricks for Open-Vocabulary Semantic Segmentation
- 24 November 2024
- Published by Springer Nature
- p. 320-337
CLIP-DINOiser: Teaching CLIP a Few DINO Tricks for Open-Vocabulary Semantic Segmentation
- 20 August 2024
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 133 (2) , 781-808
Unsupervised Object Localization in the Era of Self-Supervised ViTs: A Survey
- 20 August 2024
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 133 (2) , 781-808
Unsupervised Object Localization in the Era of Self-Supervised ViTs: A Survey
- Open Access
MILAN: Milli-Annotations for Lidar Semantic Segmentation
Annotating lidar point clouds for autonomous driving is a notoriously expensive and time-consuming task. In this work, we show that the quality of recent self-supervised lidar scan representations allows a great reduction of the annotation cost. Our method has two main steps. First, we show that self-supervised representations allow a simple and direct selection of highly informative lidar scans to annotate: training a network on these selected scans leads to much better results than a random selection of scans and, more interestingly, to results on par with selections made by SOTA active learning methods. In a second step, we leverage the same self-supervised representations to cluster points in our selected scans. Asking the annotator to classify each cluster, with a single click per cluster, then permits us to close the gap with fully-annotated training sets, while only requiring one thousandth of the point labels.
Open AccessMILAN: Milli-Annotations for Lidar Semantic Segmentation
Annotating lidar point clouds for autonomous driving is a notoriously expensive and time-consuming task. In this work, we show that the quality of recent self-supervised lidar scan representations allows a great reduction of the annotation cost. Our method has two main steps. First, we show that self-supervised representations allow a simple and direct selection of highly informative lidar scans to annotate: training a network on these selected scans leads to much better results than a random selection of scans and, more interestingly, to results on par with selections made by SOTA active learning methods. In a second step, we leverage the same self-supervised representations to cluster points in our selected scans. Asking the annotator to classify each cluster, with a single click per cluster, then permits us to close the gap with fully-annotated training sets, while only requiring one thousandth of the point labels.
- Open Access
Drive&Segment: Unsupervised Semantic Segmentation of Urban Scenes via Cross-modal Distillation
This work investigates learning pixel-wise semantic image segmentation in urban scenes without any manual annotation, just from the raw non-curated data collected by cars which, equipped with cameras and LiDAR sensors, drive around a city. Our contributions are threefold. First, we propose a novel method for cross-modal unsupervised learning of semantic image segmentation by leveraging synchronized LiDAR and image data. The key ingredient of our method is the use of an object proposal module that analyzes the LiDAR point cloud to obtain proposals for spatially consistent objects. Second, we show that these 3D object proposals can be aligned with the input images and reliably clustered into semantically meaningful pseudo-classes. Finally, we develop a cross-modal distillation approach that leverages image data partially annotated with the resulting pseudo-classes to train a transformer-based model for image semantic segmentation. We show the generalization capabilities of our method by testing on four different testing datasets (Cityscapes, Dark Zurich, Nighttime Driving and ACDC) without any finetuning, and demonstrate significant improvements compared to the current state of the art on this problem. See project webpage https://vobecant.github.io/DriveAndSegment/ for the code and more.
Open AccessDrive&Segment: Unsupervised Semantic Segmentation of Urban Scenes via Cross-modal Distillation
This work investigates learning pixel-wise semantic image segmentation in urban scenes without any manual annotation, just from the raw non-curated data collected by cars which, equipped with cameras and LiDAR sensors, drive around a city. Our contributions are threefold. First, we propose a novel method for cross-modal unsupervised learning of semantic image segmentation by leveraging synchronized LiDAR and image data. The key ingredient of our method is the use of an object proposal module that analyzes the LiDAR point cloud to obtain proposals for spatially consistent objects. Second, we show that these 3D object proposals can be aligned with the input images and reliably clustered into semantically meaningful pseudo-classes. Finally, we develop a cross-modal distillation approach that leverages image data partially annotated with the resulting pseudo-classes to train a transformer-based model for image semantic segmentation. We show the generalization capabilities of our method by testing on four different testing datasets (Cityscapes, Dark Zurich, Nighttime Driving and ACDC) without any finetuning, and demonstrate significant improvements compared to the current state of the art on this problem. See project webpage https://vobecant.github.io/DriveAndSegment/ for the code and more.
- 23 October 2022
- Published by Springer Nature
- p. 478-495
Drive&Segment: Unsupervised Semantic Segmentation of Urban Scenes via Cross-Modal Distillation
- 23 October 2022
- Published by Springer Nature
- p. 478-495
Drive&Segment: Unsupervised Semantic Segmentation of Urban Scenes via Cross-Modal Distillation