Zobrazeno 1 - 10
of 117
pro vyhledávání: '"Bursuc, Andrei"'
Autor:
Vu, Tuan-Hung, Valle, Eduardo, Bursuc, Andrei, Kerssies, Tommie, de Geus, Daan, Dubbelman, Gijs, Qian, Long, Zhu, Bingke, Chen, Yingying, Tang, Ming, Wang, Jinqiao, Vojíř, Tomáš, Šochman, Jan, Matas, Jiří, Smith, Michael, Ferrie, Frank, Basu, Shamik, Sakaridis, Christos, Van Gool, Luc
We propose the unified BRAVO challenge to benchmark the reliability of semantic segmentation models under realistic perturbations and unknown out-of-distribution (OOD) scenarios. We define two categories of reliability: (1) semantic reliability, whic
Externí odkaz:
http://arxiv.org/abs/2409.15107
Autor:
de Moreau, Simon, Almehio, Yasser, Bursuc, Andrei, El-Idrissi, Hafid, Stanciulescu, Bogdan, Moutarde, Fabien
Nighttime camera-based depth estimation is a highly challenging task, especially for autonomous driving applications, where accurate depth perception is essential for ensuring safe navigation. We aim to improve the reliability of perception systems a
Externí odkaz:
http://arxiv.org/abs/2409.08031
This paper introduces FUNGI, Features from UNsupervised GradIents, a method to enhance the features of vision encoders by leveraging self-supervised gradients. Our method is simple: given any pretrained model, we first compute gradients from various
Externí odkaz:
http://arxiv.org/abs/2407.10964
Autor:
Wysoczańska, Monika, Vobecky, Antonin, Cardiel, Amaia, Trzciński, Tomasz, Marlet, Renaud, Bursuc, Andrei, Siméoni, Oriane
Recent VLMs, pre-trained on large amounts of image-text pairs to align both modalities, have opened the way to open-vocabulary semantic segmentation. Given an arbitrary set of textual queries, image regions are assigned the closest query in feature s
Externí odkaz:
http://arxiv.org/abs/2407.05061
Autor:
Xu, Yihong, Zablocki, Éloi, Boulch, Alexandre, Puy, Gilles, Chen, Mickael, Bartoccioni, Florent, Samet, Nermin, Siméoni, Oriane, Gidaris, Spyros, Vu, Tuan-Hung, Bursuc, Andrei, Valle, Eduardo, Marlet, Renaud, Cord, Matthieu
Motion forecasting is crucial in autonomous driving systems to anticipate the future trajectories of surrounding agents such as pedestrians, vehicles, and traffic signals. In end-to-end forecasting, the model must jointly detect and track from sensor
Externí odkaz:
http://arxiv.org/abs/2406.08113
Autor:
Sirko-Galouchenko, Sophia, Boulch, Alexandre, Gidaris, Spyros, Bursuc, Andrei, Vobecky, Antonin, Pérez, Patrick, Marlet, Renaud
We introduce a self-supervised pretraining method, called OccFeat, for camera-only Bird's-Eye-View (BEV) segmentation networks. With OccFeat, we pretrain a BEV network via occupancy prediction and feature distillation tasks. Occupancy prediction prov
Externí odkaz:
http://arxiv.org/abs/2404.14027
Autor:
Franchi, Gianni, Laurent, Olivier, Leguéry, Maxence, Bursuc, Andrei, Pilzer, Andrea, Yao, Angela
Deep Neural Networks (DNNs) are powerful tools for various computer vision tasks, yet they often struggle with reliable uncertainty quantification - a critical requirement for real-world applications. Bayesian Neural Networks (BNN) are equipped for u
Externí odkaz:
http://arxiv.org/abs/2312.15297
Autor:
Wysoczańska, Monika, Siméoni, Oriane, Ramamonjisoa, Michaël, Bursuc, Andrei, Trzciński, Tomasz, Pérez, Patrick
The popular CLIP model displays impressive zero-shot capabilities thanks to its seamless interaction with arbitrary text prompts. However, its lack of spatial awareness makes it unsuitable for dense computer vision tasks, e.g., semantic segmentation,
Externí odkaz:
http://arxiv.org/abs/2312.12359
Generalization to new domains not seen during training is one of the long-standing challenges in deploying neural networks in real-world applications. Existing generalization techniques either necessitate external images for augmentation, and/or aim
Externí odkaz:
http://arxiv.org/abs/2311.17922
Autor:
Puy, Gilles, Gidaris, Spyros, Boulch, Alexandre, Siméoni, Oriane, Sautier, Corentin, Pérez, Patrick, Bursuc, Andrei, Marlet, Renaud
Self-supervised image backbones can be used to address complex 2D tasks (e.g., semantic segmentation, object discovery) very efficiently and with little or no downstream supervision. Ideally, 3D backbones for lidar should be able to inherit these pro
Externí odkaz:
http://arxiv.org/abs/2310.17504