An international team based in Paris, which conducts AI research for Valeo automotive applications, in collaboraton with world-class academics. Our main research is towards better, clearer & safer automotive AI. See our papers, projects, codes, posts and tweets.
Florent Bartoccioni, PhD student
Hédi Ben-younes, research scientist | scholar | twitter
Alexandre Boulch, research scientist | page | scholar| github | twitter
Andrei Bursuc, research scientist | page | scholar | github | twitter
Laura Calem, PhD student | github | twitter
Mickaël Chen, research scientist | page | scholar | github
Charles Corbière, PhD student | page | scholar | github | twitter
Matthieu Cord, principal scientist | page | scholar | twitter
Spyros Gidaris, research scientist | scholar | github
David Hurych, research scientist | scholar
Himalaya Jain, research scientist | page | scholar | github
Renaud Marlet, principal scientist | page | scholar
Arthur Ouaknine, PhD student | page | scholar | twitter
Patrick Pérez, scientific director | page | scholar
Gilles Puy, research scientist | page | scholar
Julien Rebut, research scientist | scholar
Simon Roburin, PhD student | page
Antoine Saporta, PhD student | scholar
Tristan Schultz, research engineer
Oriane Siméoni, research scientist | page | scholar | github
Huy Van Vo, PhD student | scholar | github
Tuan-Hung Vu, research scientist | page | scholar | github | twitter
Eloi Zablocki, research scientist | scholar | twitter
Léon Zheng, PhD student
Multi-sensor perception — Automated driving relies first on a variety of sensors, like Valeo’s fish-eye cameras, LiDARs, radars and ultrasonics. Exploiting at best the outputs of each of these sensors at any instant is fundamental to understand the complex environment of the vehicle and gain robustness. To this end, we explore various machine learning approaches where sensors are considered either in isolation (as radar in Carrada at ICPR’20) or collectively (as in xMUDA at CVPR’20).
3D perception — Each sensor delivers information about the 3D world around the vehicle. Making sense of this information in terms of drivable space and important objects (road users, curb, obstacles, street furnitures) in 3D is required for the driving system to plan and act in the safest and most comfortable way. This encompasses several challenging tasks, in particular detection and segmentation of objects in point clouds as in FKAConv at ACCV’20.
Frugal learning — Collecting diverse enough data, and annotating it precisely, is complex, costly and time-consuming. To reduce dramatically these needs, we explore various alternatives to fully-supervised learning, e.g, training that is unsupervised (as rOSD at ECCCV’20), self-supervised (as BoWNet at CVPR’20 and OBoW at CVPR’21), semi-supervised, active, zero-shot (as ZS3 at NeurIPS’19) or few-shot. We also investigate training with fully-synthetic data (in combination with unsupervised domain adaptation) and with GAN-augmented data (as with Semantic Palette at CVPR’21 and DummyNet at AAAI’21).
Domain adaptation — Deep learning and reinforcement learning are key technologies for autonomous driving. One of the challenges they face is to adapt to conditions which differ from those met during training. To improve systems’ performance in such situations, we explore so-called “domain adaptation” techniques, as in AdvEnt at CVPR’19 and DADA its extension at ICCV’19.
Reliability — When the unexpected happens, when the weather badly degrades, when a sensor gets blocked, the embarked perception system should continue working or, at least, diagnose the situation to react accordingly, e.g., by calling an alternative system or the human driver. With this in mind, we investigate ways to improve the robustness of neural nets to input variations, including to adversarial attacks, and to predict automatically the performance and the confidence of their predictions as in ConfidNet at NeurIPS’19.
Driving in action — Getting from sensory inputs to car control goes either through a modular stack (perception > localization > forecast > planning > actuation) or, more radically, through a single end-to-end model. We work on both strategies, more specifically on action forecasting, automatic interpretation of decisions taken by a driving system, and reinforcement / imitation learning for end-to-end systems (as in RL work at CVPR’20).
Core Deep Learning — Deep learning being now a key component of AD systems, it is important to get a better understanding of its inner workings, in particular the link between the specifics of the learning optimization and the key properties (performance, regularity, robustness, generalization) of the trained models. Among other things, we investigate the impact of popular batch normalization on standard learning procedures and the ability to learn through unsupervised distillation.
Code and data
- MVRSS: Multi-view radar semantic segmentation (ICCV’21)
- ObsNet: Out-Of-Distribution detection by learning from local adversarial attacks in semantic segmentation (ICCV’21)
- Semantic Palette: Guiding scene generation with class proportions (CVPR’21)
- Attributes with Fields: Detecting 32 pedestrian attributes with composite fields (T-ITS)
- OBoW: Online BoW generation for unsupervised representation learning (CVPR’21)
- DummyNet: Artificial Dummies for Urban Dataset Augmentation (AAAI’21)
- CARRADA (dataset): Camera and Automotive Radar with Range-Angle-Doppler Annotations dataset (ICPR’20)
- ESL: Entropy-guided Self-supervised Learning for Domain Adaptation in Semantic Segmentation (workshop CVPR’20)
- FLOT: Scene flow on point clouds guided by optimal transport (ECCV’20)
- AdamSRT: Adam exploiting BN-induced pherical invariance of CNN (arXiv 2020)
- LightConvPoint: Convolution for points (ACCV’20)
- xMUDA: Cross-modal UDA for 3D semantic segmentation (CVPR’20)
- LearningByCheating: End-to-End driving using implicit affordances (CVPR’20)
- rOSD: Unsupervised object discovery at scale (ECCV’20)
- ConvPoint: Convolutions for unstructured point clouds (Computer \& Graphics 2020)
- BEEF: Driving behavior explanation with multi-level fusion (workshop NeurIPS’20)
- Woodscape: Driving fisheye multi-task dataset (ICCV’19)
- ZS3: Zero-Shot Semantic Segmentation (NeurIPS’19)
- BF3S: Boosting few-shot visual learning with self-supervision (ICCV’19)
- ConfidNet: Addressing failure prediction by learning model confidence (NeurIPS’19)
- Rainbow-IQN Ape-X: effective RL combination for Atari games
- DADA: Depth-aware Domain Adaptation in Semantic Segmentation (ICCV’19)
- AdvEnt: Adversarial Entropy minimization for domain adaptation in semantic segmentation (CVPR’19)
- OSD: Unsupervised object discovery as optimization (CVPR’19)
CNAM, Paris (Nicolas Thome)
CTU, Prague (Josef Sivic)
EPFL, Lausanne (Alexandre Alahi)
ENS & Inria, Lyon (Rémi Gribonval)
Inria & PR[AI]RIE, Paris (Jean Ponce)
Inria, Grenoble (Karteek Alahari)
MPI, Saarbrücken (Christian Theobalt)
Ponts, Paris (Mathieu Aubry, David Picard)
Sorbonne, Paris (Matthieu Cord)
Télécom, Paris (Florence Tupin, Alasdair Newson, Florence d’Alché-Buc)
- 09/2021: The team moves in the beautiful new Valeo headquarter, 100 rue de Courcelles, in Paris.
- 08/2021: Paper on Handling new target classes in semantic segmentation with domain adaptation accpeted in CVIU.
- 08/2021: Paper on Detecting 32 pedestrian attributes for autonomous vehicles with code accepted in T-IST.
- 08/2021: Code for our ICCV’21 paper “Multi-view radar semantic segmentation”.
- 08/2021: Code for our ICCV’21 paper “Triggering Failures: Out-Of-Distribution detection by learning from local adversarial attacks in Semantic Segmentation”.
- 08/2021 Renaud Marlet among the Outstanding Reviewers of ICCV’21.
- 07/2021: Matthieu Cord on self-supervised learning in French newspaper Le Monde.
- 07/2021: Six papers accepted at ICCV’21 (25.9% acceptance rate).
- 07/2021: Code for our CVPR’21 paper “Semantic Palette: Guiding scene generation with class proportions”.
- 06/2021: Spyros Gidaris to serve as Area Chair for CVPR 2022.
- 06/2021: Reanud Marlet to serve as Meta-reviewer for BMVC 2021.
- 06/2021: Valeo.ai participates to CVPR’21 presenting three papers, co-organizing a tutorial on self-supervised learning and the OmniCV workshop and delivering keynotes at SAIAD and Vision4AllSeason workshops.
- 06/2021: Matthieu Cord serves as Area Chair for NeurIPS 2021.
- 05/2021 Alexandre Boulch, Andrei Bursuc, Matthieu Cord, Renaud Marlet, Spyros Gidaris and Tuan-Hung Vu among the Outstanding Reviewers of CVPR’21.
- 05/2021: Paper on Confidence estimation via auxiliary models accepted in IEEE T-PAMI.
- 04/2021: Woodscape Challenge on fisheye semantic scene segmentation in conjunctin with CVPR’21 OmniCV workshop.
- 03/2021: Marin Toromanoff defends his PhD at MinesParis, committee: O. Pietquin, Th. Chateau, P.-Y. Oudeyer, R. Munos, Ch. Gagne, F. Moutarde, X. Perrotton.
- 03/2021: Three papers accepted at CVPR’21 (23.7% acceptance rate).
- 02/2021: Matthieu Cord delivers keynote at Machine Learning Prague.
- 02/2021: Blog post on the explainability of neural driving models.
- 01/2021: Preprint on Cross-modal learning for domain adaptation in 3D semantic segmentation.
- 01/2021: Preprint on the Explainability of vision-based autonomous driving systems.
- 12/2020: Preprint on Online BoW prediction for unsupervised representation learning with code.
- 12/2020: Valeo participates with keynote and posters to ML4AD virtual workshop at NeurIPS’20.
- 12/2020: One paper in collaboration with CTU Prague accepted at AAAI’21.
- 11/2020: IV2020 workshop on 3D Deep Learning for Autonomous Driving (3D-DLAD).
- 10/2020: Dataset for our ICPR’20 paper “CARRADA Dataset: Camera and Automotive Radar with Range-Angle-Doppler Annotations” (CARRADA).
- 10/2020: Four team members (Andrei, Matthieu, Patrick and Spyros) acknowledged as Outstanding Reviewers at NeurIPS’20.
- 07/2020: Code for our ECCV’20 paper “FLOT: Scene flow on point clouds guided by optimal transport” (FLOT).
- 06/2020: Seven papers accepted at ECCV’20 (27% acceptance rate).
- 06/2020: Four team members (Alexandre, Andrei, Matthieu and Renaud) acknowledged as Outstanding Reviewers at CVPR’20.
- 06/2020: Valeo.ai participates to (virtual) CVPR’20, presenting 5 papers in main conference, delivering tutorials on annotation-efficient learning, co-organizing the OmniCV workshop and presenting keynote at the SAIAD workshop.
- 06/2020: Maximilian Jaritz defends his PhD at Inria Paris on “2D-3D Scene Understanding for Autonomous Driving” (reviewers: V. Lepetit and G. Brostow, external examiners: A. Dai and F. Jurie).
- 06/2020: Code for our CVPR’20 paper “xMUDA: Cross-Modal Unsupervised Domain Adaptation for 3D Semantic Segmentation” (xMUDA).
- 04/2020: Eloi Zablocki receives the Second Best Thesis Prize from the French Association for AI.
- 02/2020: Code for our NeurIPS’19 paper “Zero-Shot Semantic Segmentation” (ZS3).
- 02/2020: Five papers accepted at CVPR’20 (22% acceptance rate), inc. one oral.
- 01/2020: Spyros Gidaris, Andrei Bursuc and Karteek Alahari (Inria) to deliver a tutorial on Few-Shot, Self-Supervised, and Incremental Learning at CVPR’20.
- 01/2020: Pedestrian monitoring demo at CES, Las Vegas.
- 12/2019: Medium post: Is deep Reinforcement Learning really superhuman on Atari?
- 12/2019: Code for our ICCV’19 paper “Boosting few-shot visual learning with self-supervision” (BF3S).
- 12/2019: Code for our ICCV’19 paper “DADA: Depth-Aware Domain Adaptation in semantic segmentation” (DADA).
- 11/2019: Spyros Gidaris receives the Thesis Prize from Université Paris Est.
- 10/2019: Valeo.ai researchers present 5 papers at ICCV’19 in Seoul, Korea, and Valeo participates to associated workshops on Autonomous Driving and on Autonomous Navigation in Unconstrained Environments.
- 10/2019: PRAIRIE research institute is officially launched, with a nice day of talks and pannels (inc. one on future mobility, program in French). Followed by PRAIRIE AI Summer School (PAISS), where Patrick Pérez delivered a lecture (slides).
- 09/2019: Code of our NeurIPS’19 paper “Addressing failure prediction by learning model confidence” (ConfidNet).
- 09/2019: Work of Marin Toromanoff et al. discussed by Andrew Ng in The Batch (deeplearning.ai newsletter).
- 09/2019: Two papers accepted at NeurIPS’19 (21% acceptance rate).
- 09/2019: Matthieu Cord among NeurIPS’19 top contributors.
- 07/2029: Medium post: ADVENT: Adversarial entropy minimization for domain adaptation in semantic segmentation.
- 07/2019: Three papers accepted at ICCV’19 (24% acceptance rate), including one oral (4.6% acceptance rate).
- 07/2019: Code of our CVPR’19 paper “AdvEnt: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation” is available on valeo.ai github.
- 07/2019: Marin Toromanoff (PhD student with Mines ParisTech, Valeo DAR and Valeo.ai) ranks 1st on Track 2 of Carla Challenge 2019, and 2nd on Track 1.
- 06/2019: Spyros Gidaris receives the Best Thesis Prize from Ponts Foundation.
- 06/2019: Valeo.ai researchers present 8 papers (25% acceptance rate), including 4 orals (5.6% acceptance rate), at CVPR’19. Patrick Pérez delivers keynote on “Sustainable supervision with application to autonomous driving” at the Safe AI for Automated Driving (SAIAD) CVPR’19 Workshop.
- 05/2019: Hedi Ben-younes defends his PhD at Sorbonne Université, committee: M. Cord, V. Ferrari, Y. LeCun, P. Pérez, L. Soulier, N. Thome, J. Verbeek, Ch. Wolf.
- 05/2019: Himalaya Jain receives the Best Thesis Prize from Rennes 1 Foundation.
- 05/2019: Valeo is proud to be part of Prairie, the new Paris Interdisciplinary Artificial Intelligence Institute.
- With seven other France’s global industry players, Valeo signs a Manifesto on AI for Industry.
- Jacques Aschenbroich (Chairman and CEO of Valeo) on AI and valeo.ai.
- Valeo Drive4u automated car in Paris center, a world premiere!
- Patrick Pérez on the start of Valeo.ai.
- Valeo Cruise4u automated car, 24h on Parisian ringroad.
Marin Toromanoff, PhD student (scholar), now at Valeo Driving Assistance Research
Maxime Bucher, research scientist (page,scholar), now at Augustus Intelligence
Maximilian Jaritz, PhD student (page, scholar), now at Amazon
Gabriel de Marmiesse, research engineer (github), now at EarthCube
Emilie Wirbel, research scientist (scholar), now at NVidia