1.8k citations
- CERMICSFR274 papers
- Centre National de la Recherche ScientifiqueFR162 papers
- Institut national de recherche en sciences et technologies du numériqueFR159 papers
- Pôle de recherche et d'enseignement supérieur Université Paris-EstFR92 papers
- Laboratoire NavierFR82 papers
- Laboratoire d'Informatique Gaspard-MongeFR46 papers
- Paris-Est SupFR40 papers
- Université Gustave EiffelFR39 papers
- MATHERIALS: MATHematics for MatERIALSFR27 papers
- Commissariat à l'Énergie Atomique et aux Énergies AlternativesFR26 papers
- Sorbonne UniversitéFR26 papers
- Université Paris-SaclayFR21 papers
5 papers · 2 filters
Localizing Objects with Self-Supervised Transformers and no Labels
Oriane Siméoni, Gilles Puy, Huy V. Vo +6
Localizing objects in image collections without supervision can help to avoid expensive annotation campaigns. We propose a simple approach to this problem, that leverages the activ…
Torch.manual_seed(3407) is all you need: On the influence of random seeds in deep learning architectures for computer vision
David Picard
In this paper I investigate the effect of random seed selection on the accuracy when using popular deep learning architectures for computer vision. I scan a large amount of seeds (…
Visual Correspondence Hallucination
Hugo Germain, Vincent Lepetit, Guillaume Bourmaud
Given a pair of partially overlapping source and target images and a keypoint in the source image, the keypoint's correspondent in the target image can be either visible, occluded…
Learning to Better Segment Objects from Unseen Classes with Unlabeled Videos
Yuming Du, Yang Xiao, Vincent Lepetit
The ability to localize and segment objects from unseen classes would open the door to new applications, such as autonomous object learning in active vision. Nonetheless, improving…
Monte Carlo Scene Search for 3D Scene Understanding
Shreyas Hampali, Sinisa Stekovic, Sayan Deb Sarkar +3
We explore how a general AI algorithm can be used for 3D scene understanding to reduce the need for training data. More exactly, we propose a modification of the Monte Carlo Tree S…