Nicolas Hueber
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Nicolas Hueber has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Frederic Dufaux
Université Paris-Saclay, CNRS, CentraleSupélec
4 shared publications Mohamed-Cherif Rahal
4 shared publications- Florent Chiaroni
ETS Montreal and INRS, Montreal, QC, Canada
2 shared publications - Florent Chiaroni
Department of delegated driving (VEH08) Perception team VEDECOM Institute 23 bis Allee des Marronniers 78000 Versailles France
2 shared publications - Ghazaleh Khodabandelou
Department of new uses (MOB05) Artificial Intelligence team VEDECOM Institute 23 bis Allee des Marronniers 78000 Versailles France
2 shared publications - Antoine Manzanera
Unité d’Informatique et d’Ingénierie des Systèmes (U2IS), ENSTA Paris, Institut Polytechnique de Paris, Palaiseau, France
1 shared publication
Latest Publications
- 24 December 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Magazine
- Vol. 38 (1) , 31-41
Self-Supervised Learning for Autonomous Vehicles Perception: A Conciliation Between Analytical and Learning Methods
The interest in autonomous driving has continuously increased in the last two decades. However, to be adopted, such critical systems need to be safe. Concerning the perception of the ego-vehicle environment, the literature has investigated two different types of methods. On the one hand, traditional analytical methods generally rely on handcrafted designs and features while on the other hand, learning methods aim at designing their own appropriate representation of the observed scene.
- 24 December 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Magazine
- Vol. 38 (1) , 31-41
Self-Supervised Learning for Autonomous Vehicles Perception: A Conciliation Between Analytical and Learning Methods
The interest in autonomous driving has continuously increased in the last two decades. However, to be adopted, such critical systems need to be safe. Concerning the perception of the ego-vehicle environment, the literature has investigated two different types of methods. On the one hand, traditional analytical methods generally rely on handcrafted designs and features while on the other hand, learning methods aim at designing their own appropriate representation of the observed scene.
- 1 November 2020
- Published by Elsevier in Pattern Recognition
- Vol. 107
Counter-examples generation from a positive unlabeled image dataset
- 1 November 2020
- Published by Elsevier in Pattern Recognition
- Vol. 107
Counter-examples generation from a positive unlabeled image dataset
- Open Access
Self-supervised learning for autonomous vehicles perception: A conciliation between analytical and learning methods
Nowadays, supervised deep learning techniques yield the best state-of-the-art prediction performances for a wide variety of computer vision tasks. However, such supervised techniques generally require a large amount of manually labeled training data. In the context of autonomous vehicles perception, this requirement is critical, as the distribution of sensor data can continuously change and include several unexpected variations. It turns out that a category of learning techniques, referred to as self-supervised learning (SSL), consists of replacing the manual labeling effort by an automatic labeling process. Thanks to their ability to learn on the application time and in varying environments, state-of-the-art SSL techniques provide a valid alternative to supervised learning for a variety of different tasks, including long-range traversable area segmentation, moving obstacle instance segmentation, long-term moving obstacle tracking, or depth map prediction. In this tutorial-style article, we present an overview and a general formalization of the concept of self-supervised learning (SSL) for autonomous vehicles perception. This formalization provides helpful guidelines for developing novel frameworks based on generic SSL principles. Moreover, it enables to point out significant challenges in the design of future SSL systems.
Open AccessSelf-supervised learning for autonomous vehicles perception: A conciliation between analytical and learning methods
Nowadays, supervised deep learning techniques yield the best state-of-the-art prediction performances for a wide variety of computer vision tasks. However, such supervised techniques generally require a large amount of manually labeled training data. In the context of autonomous vehicles perception, this requirement is critical, as the distribution of sensor data can continuously change and include several unexpected variations. It turns out that a category of learning techniques, referred to as self-supervised learning (SSL), consists of replacing the manual labeling effort by an automatic labeling process. Thanks to their ability to learn on the application time and in varying environments, state-of-the-art SSL techniques provide a valid alternative to supervised learning for a variety of different tasks, including long-range traversable area segmentation, moving obstacle instance segmentation, long-term moving obstacle tracking, or depth map prediction. In this tutorial-style article, we present an overview and a general formalization of the concept of self-supervised learning (SSL) for autonomous vehicles perception. This formalization provides helpful guidelines for developing novel frameworks based on generic SSL principles. Moreover, it enables to point out significant challenges in the design of future SSL systems.
- Open Access
Generating Relevant Counter-Examples from a Positive Unlabeled Dataset for Image Classification
With surge of available but unlabeled data, Positive Unlabeled (PU) learning is becoming a thriving challenge. This work deals with this demanding task for which recent GAN-based PU approaches have demonstrated promising results. Generative adversarial Networks (GANs) are not hampered by deterministic bias or need for specific dimensionality. However, existing GAN-based PU approaches also present some drawbacks such as sensitive dependence to prior knowledge, a cumbersome architecture or first-stage overfitting. To settle these issues, we propose to incorporate a biased PU risk within the standard GAN discriminator loss function. In this manner, the discriminator is constrained to request the generator to converge towards the unlabeled samples distribution while diverging from the positive samples distribution. This enables the proposed model, referred to as D-GAN, to exclusively learn the counter-examples distribution without prior knowledge. Experiments demonstrate that our approach outperforms state-of-the-art PU methods without prior by overcoming their issues.
Open AccessGenerating Relevant Counter-Examples from a Positive Unlabeled Dataset for Image Classification
With surge of available but unlabeled data, Positive Unlabeled (PU) learning is becoming a thriving challenge. This work deals with this demanding task for which recent GAN-based PU approaches have demonstrated promising results. Generative adversarial Networks (GANs) are not hampered by deterministic bias or need for specific dimensionality. However, existing GAN-based PU approaches also present some drawbacks such as sensitive dependence to prior knowledge, a cumbersome architecture or first-stage overfitting. To settle these issues, we propose to incorporate a biased PU risk within the standard GAN discriminator loss function. In this manner, the discriminator is constrained to request the generator to converge towards the unlabeled samples distribution while diverging from the positive samples distribution. This enables the proposed model, referred to as D-GAN, to exclusively learn the counter-examples distribution without prior knowledge. Experiments demonstrate that our approach outperforms state-of-the-art PU methods without prior by overcoming their issues.
- Open Access
Generating Relevant Counter-Examples from a Positive Unlabeled Dataset for Image Classification
With surge of available but unlabeled data, Positive Unlabeled (PU) learning is becoming a thriving challenge. This work deals with this demanding task for which recent GAN-based PU approaches have demonstrated promising results. Generative adversarial Networks (GANs) are not hampered by deterministic bias or need for specific dimensionality. However, existing GAN-based PU approaches also present some drawbacks such as sensitive dependence to prior knowledge, a cumbersome architecture or first-stage overfitting. To settle these issues, we propose to incorporate a biased PU risk within the standard GAN discriminator loss function. In this manner, the discriminator is constrained to request the generator to converge towards the unlabeled samples distribution while diverging from the positive samples distribution. This enables the proposed model, referred to as D-GAN, to exclusively learn the counter-examples distribution without prior knowledge. Experiments demonstrate that our approach outperforms state-of-the-art PU methods without prior by overcoming their issues.
Open AccessGenerating Relevant Counter-Examples from a Positive Unlabeled Dataset for Image Classification
With surge of available but unlabeled data, Positive Unlabeled (PU) learning is becoming a thriving challenge. This work deals with this demanding task for which recent GAN-based PU approaches have demonstrated promising results. Generative adversarial Networks (GANs) are not hampered by deterministic bias or need for specific dimensionality. However, existing GAN-based PU approaches also present some drawbacks such as sensitive dependence to prior knowledge, a cumbersome architecture or first-stage overfitting. To settle these issues, we propose to incorporate a biased PU risk within the standard GAN discriminator loss function. In this manner, the discriminator is constrained to request the generator to converge towards the unlabeled samples distribution while diverging from the positive samples distribution. This enables the proposed model, referred to as D-GAN, to exclusively learn the counter-examples distribution without prior knowledge. Experiments demonstrate that our approach outperforms state-of-the-art PU methods without prior by overcoming their issues.
- 3 March 2019
- Published by Springer Nature
- p. 428-435
Bio-Inspired Perception Sensor (BIPS) Concept Analysis for Embedded Applications
- 3 March 2019
- Published by Springer Nature
- p. 428-435
Bio-Inspired Perception Sensor (BIPS) Concept Analysis for Embedded Applications