Cross-modal Learning for Domain Adaptation in 3D Semantic Segmentation

Autor: Maximilian Jaritz, Tuan-Hung Vu, Raoul de Charette, Emilie Wirbel, Patrick Perez

Publikováno v: IEEE Transactions on Pattern Analysis and Machine Intelligence
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022, 45 (2), pp.1533-1544. ⟨10.1109/TPAMI.2022.3159589⟩

Domain adaptation is an important task to enable learning when labels are scarce. While most works focus only on the image modality, there are many important multi-modal datasets. In order to leverage multi-modality for domain adaptation, we propose

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7b3cb575c4af1ccfe4ca8743ce2940a2
http://arxiv.org/abs/2101.07253

xMUDA: Cross-Modal Unsupervised Domain Adaptation for 3D Semantic Segmentation

Autor: Raoul de Charette, Patrick Pérez, Maximilian Jaritz, Emilie Wirbel, Tuan-Hung Vu

Publikováno v: Conference on Computer Vision and Pattern Recognition (CVPR)
Conference on Computer Vision and Pattern Recognition (CVPR), Jun 2020, Virtual, United States
CVPR

Unsupervised Domain Adaptation (UDA) is crucial to tackle the lack of annotations in a new domain. There are many multi-modal datasets, but most UDA approaches are uni-modal. In this work, we explore how to learn from multi-modality and propose cross

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::604c9ac0a1c03a3b88b40b65586e8481
https://hal.inria.fr/hal-02388974

A Lidar-based Dual-level Virtual Lanes Construction and Anticipation of Specific Road Infrastructure Events for Autonomous Driving

Autor: Emilie Wirbel, Amaury Breheret, Rachid Benmokhtar, Ferit Uzer

Publikováno v: 2019 IEEE Intelligent Vehicles Symposium (IV).

Autonomous vehicles require clear road markings and a high-level quality of infrastructure. This paper addresses road course detection problem in non cooperative environments (i.e. absence or poor quality of road-marking, working zones, etc.). To cop

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::6ac9912204052f60736b5d155689207c
https://doi.org/10.1109/ivs.2019.8814201

End to End Vehicle Lateral Control Using a Single Fisheye Camera

Autor: Fabien Moutarde, Xavier Perrotton, Emilie Wirbel, Marin Toromanoff, Frederic Wilhelm, Camilo Vejarano

Publikováno v: IROS
I2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2018)
I2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2018), Oct 2018, Madrid, Spain

Convolutional neural networks are commonly used to control the steering angle for autonomous cars. Most of the time, multiple long range cameras are used to generate lateral failure cases. In this paper we present a novel model to generate this data

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::fa5f51de1bead0cd29d782561eac1317
https://doi.org/10.1109/iros.2018.8594090

Humanoid robot navigation: getting localization information from vision

Autor: Fabien Moutarde, Silvere Bonnabel, Emilie Wirbel, Arnaud de La Fortelle

Publikováno v: Journal of Intelligent Systems
Journal of Intelligent Systems, Walter de Gruyter, 2014, 23 (2), pp.113-132
Journal of Intelligent Systems, Vol 23, Iss 2, Pp 113-132 (2014)
Journal of Intelligent Systems, 2014, 23 (2), pp.113-132

In this article, we present our work to provide a navigation and localization system on a constrained humanoid platform, the NAO robot, without modifying the robot sensors. First, we tried to implement a simple and light version of classic monocular

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::349535e768882d41af9ed9309c103664
https://hal-mines-paristech.archives-ouvertes.fr/hal-00949738