Institution
Valeo
Company•Paris, France•
About: Valeo is a company organization based out in Paris, France. It is known for research contribution in the topics: Heat exchanger & Clutch. The organization has 8904 authors who have published 14808 publications receiving 83614 citations. The organization is also known as: Société anonyme française du Ferodo.
Papers published on a yearly basis
Papers
More filters
••
15 Jun 2019TL;DR: This work proposes two novel, complementary methods using (i) entropy loss and (ii) adversarial loss respectively for unsupervised domain adaptation in semantic segmentation with losses based on the entropy of the pixel-wise predictions.
Abstract: Semantic segmentation is a key problem for many computer vision tasks. While approaches based on convolutional neural networks constantly break new records on different benchmarks, generalizing well to diverse testing environments remains a major challenge. In numerous real-world applications, there is indeed a large gap between data distributions in train and test domains, which results in severe performance loss at run-time. In this work, we address the task of unsupervised domain adaptation in semantic segmentation with losses based on the entropy of the pixel-wise predictions. To this end, we propose two novel, complementary methods using (i) entropy loss and (ii) adversarial loss respectively. We demonstrate state-of-the-art performance in semantic segmentation on two challenging “synthetic-2-real” set-ups and show that the approach can also be used for detection.
1,034 citations
••
TL;DR: This review summarises deep reinforcement learning algorithms, provides a taxonomy of automated driving tasks where (D)RL methods have been employed, highlights the key challenges algorithmically as well as in terms of deployment of real world autonomous driving agents, the role of simulators in training agents, and finally methods to evaluate, test and robustifying existing solutions in RL and imitation learning.
Abstract: With the development of deep representation learning, the domain of reinforcement learning (RL) has become a powerful learning framework now capable of learning complex policies in high dimensional environments. This review summarises deep reinforcement learning (DRL) algorithms and provides a taxonomy of automated driving tasks where (D)RL methods have been employed, while addressing key computational challenges in real world deployment of autonomous driving agents. It also delineates adjacent domains such as behavior cloning, imitation learning, inverse reinforcement learning that are related but are not classical RL algorithms. The role of simulators in training agents, methods to validate, test and robustify existing solutions in RL are discussed.
740 citations
••
TL;DR: In this paper, a leading-edge backscattering correction is derived, based on the solution of an equivalent Schwarzschild problem, and added to the original formula to account for all the effects due to a limited chord length, and to infer the far-field radiation off the mid-span plane.
385 citations
•
TL;DR: A novel model-based deep convolutional autoencoder that addresses the highly challenging problem of reconstructing a 3D human face from a single in-the-wild color image and can be trained end-to-end in an unsupervised manner, which renders training on very large real world data feasible.
Abstract: In this work we propose a novel model-based deep convolutional autoencoder that addresses the highly challenging problem of reconstructing a 3D human face from a single in-the-wild color image. To this end, we combine a convolutional encoder network with an expert-designed generative model that serves as decoder. The core innovation is our new differentiable parametric decoder that encapsulates image formation analytically based on a generative model. Our decoder takes as input a code vector with exactly defined semantic meaning that encodes detailed face pose, shape, expression, skin reflectance and scene illumination. Due to this new way of combining CNN-based with model-based face reconstruction, the CNN-based encoder learns to extract semantically meaningful parameters from a single monocular input image. For the first time, a CNN encoder and an expert-designed generative model can be trained end-to-end in an unsupervised manner, which renders training on very large (unlabeled) real world data feasible. The obtained reconstructions compare favorably to current state-of-the-art approaches in terms of quality and richness of representation.
355 citations
••
01 Oct 2017
TL;DR: A novel model-based deep convolutional autoencoder that addresses the highly challenging problem of reconstructing a 3D human face from a single in-the-wild color image and can be trained end-to-end in an unsupervised manner, which renders training on very large real world data feasible.
Abstract: In this work we propose a novel model-based deep convolutional autoencoder that addresses the highly challenging problem of reconstructing a 3D human face from a single in-the-wild color image. To this end, we combine a convolutional encoder network with an expert-designed generative model that serves as decoder. The core innovation is the differentiable parametric decoder that encapsulates image formation analytically based on a generative model. Our decoder takes as input a code vector with exactly defined semantic meaning that encodes detailed face pose, shape, expression, skin reflectance and scene illumination. Due to this new way of combining CNN-based with model-based face reconstruction, the CNN-based encoder learns to extract semantically meaningful parameters from a single monocular input image. For the first time, a CNN encoder and an expert-designed generative model can be trained end-to-end in an unsupervised manner, which renders training on very large (unlabeled) real world data feasible. The obtained reconstructions compare favorably to current state-of-the-art approaches in terms of quality and richness of representation.
316 citations
Authors
Showing all 8912 results
Name | H-index | Papers | Citations |
---|---|---|---|
Duong Nguyen | 98 | 674 | 47332 |
Patrick Pérez | 60 | 274 | 25095 |
Francis C. M. Lau | 57 | 680 | 12306 |
Matthieu Cord | 46 | 265 | 7387 |
Thierry Marie Guerra | 44 | 254 | 8250 |
Minsu Cho | 37 | 115 | 4642 |
Stéphane Moreau | 36 | 374 | 5684 |
Geraint W. Jewell | 34 | 138 | 4229 |
John McDonald | 28 | 117 | 4245 |
Christian Witt | 28 | 66 | 4624 |
Gang Yang | 27 | 96 | 3150 |
Michel Roger | 27 | 109 | 2856 |
Renaud Marlet | 26 | 105 | 2576 |
Eric Semail | 25 | 151 | 2381 |
Senthil Yogamani | 24 | 128 | 2363 |