Valeo.ai publications

2023

Rewarded soups: towards Pareto-optimal alignment by interpolating weights fine-tuned on diverse rewards
A. Ramé, G. Couairon, M. Shukor, C. Dancette, J.-B. Gaya, L. Soulier, M. Cord
NeurIPS 2023

Unifying GANs and Score-Based Diffusion as Generative Particle Models
J.-Y. Franceschi, M. Gartrell, L. Dos Santos, Th. Issenhuth, E. de Bézenac, Mi. Chen, A. Rakotomamonjy
NeurIPS 2023

Resilient Multiple Choice Learning: A learned scoring scheme with application to audio scene analysis
V. Letzelter, M. Fontaine, M. Chen, P. Pérez, S. Essid, G. Richard
NeurIPS 2023

POP-3D: Open-Vocabulary 3D Occupancy Prediction from Images
A. Vobecky, O. Siméoni, D. Hurych, S. Gidaris, A. Bursuc, P. Pérez, J. Sivic
NeurIPS 2023

Decaf: Monocular Deformation Capture for Face and Hand Interactions
S. Shimada, V. Golyanik, P. Pérez, Ch. Theobalt
Siggrah Asia 2023

PØDA: Prompt-driven Zero-shot Domain Adaptation
M. Fahes, T.-H. Vu, A. Bursuc, P. Pérez, R. de Charette
ICCV 2023

Using a Waffle Iron for Automotive Point Cloud Semantic Segmentation
G. Puy, A. Boulch, R. Marlet
ICCV 2023 [code]

You Never Get a Second Chance To Make a Good First Impression:Seeding Active Learning for 3D Semantic Segmentation
N. Samet, O. Siméoni, G. Puy, G. Ponimatkin, R. Marlet, V. Lepetit
ICCV 2023

Zero-shot spatial layout conditioning for text-to-image diffusion models
G. Couairon, M. Careil, M. Cord, S. Lathuilière, J. Verbeek
ICCV 2023

eP-ALM: Efficient Perceptual Augmentation of Language Models
M. Shukor, C. Dancette, M. Cord
ICCV 2023

OCTET: Object-aware Counterfactual Explanations
M. Zemni, M. Chen, É. Zablocki, H. Ben-Younes, P. Pérez, M. Cord
CVPR 2023 [code]

RangeViT: Towards Vision Transformers for 3D Semantic Segmentation in Autonomous Driving
A. Ando, S. Gidaris, A. Bursuc, G. Puy, A. Boulch, R. Marlet
CVPR 2023 [code]

Unsupervised object localization: observing the background to discover objects
O. Siméoni, Ch. Sekkat, G. Puy, A. Vobecky, E. Zablocki, P. Pérez
CVPR 2023 [code]

ALSO: Automotive Lidar Self-supervision by Occupancy estimation
A. Boulch. C. Sautier, B. Michele, G. Puy, R. Marlet
CVPR 2023 [code]

CoMFormer: Continual learning in semantic and panoptic segmentation
F. Cermelli, M. Cord, A. Douillard
CVPR 2023

Improving Selective VQA by learning from your peers
C. Dancette, S. Whitehead, R. Maheshwary, R. Vedantam, S. Scherer, X. Chen, M. Cord, M. Rohrbach
CVPR 2023

Self-supervised learning with rotation-invariant kernels
L. Zheng, G. Puy, E. Riccietti, P. Pérez, R. Gribonval
ICLR 2023 [code]

Packed Ensembles for efficient uncertainty estimation
O. Laurent, A. Lafage, E. Tartaglione, G. Daniel, J.-M. Martinez, A. Bursuc, G. Franchi
ICLR 2023 [code]

2022

LaRa: Latents and Rays for multi-camera bird’s-eye-view semantic segmentation
F. Bartoccioni, É. Zablocki, A. Bursuc, P. Pérez, M. Cord, K. Alahari
CoRL 2022 [code]

Drive&Segment: Unsupervised semantic segmentation of urban scenes via cross-modal distillation
A. Vobecky, D. Hurych, O. Siméoni, S. Gidaris, A. Bursuc, P. Pérez, J. Sivic
ECCV 2022 [page,code,demo]

Active learning strategies for weakly-supervised object detection
H.V. Ho, O. Siméoni, S. Gidaris, A. Bursuc, P. Pérez, J. Ponce
ECCV 2022 [code]

STEEX: Steering Counterfactual Explanations with Semantics
P. Jacob, É. Zablocki, H. Ben-Younes, M. Chen, P. Pérez, M. Cord
ECCV 2022 [code]

What to hide to your student: Attention-guided masked image modeling
I. Kakogeorgiou, S. Gidaris, B. Psomas, Y. Avrithis, A. Bursuc, K. Karantzalos, N. Komodakis
ECCV 2022 [code]

Latent discriminant deterministic uncertainty
Franchi, Yu, Bursuc, Aldea, Dubuisson, Filliat
ECCV 2022 [code]

HULC: 3D human motion capture with pose manifold sampling and dense contact guidance
S. Shimada, V. Golyanik, P. Pérez, W. Xu, Ch. Theobalt
ECCV 2022 [page and data]

A neural tangent kernel perspective of GANs
J.-Y. Franceschi, E. de Bézenac, I. Ayed, M. Chen, S. Lamprier, P. Gallinari
ICML 2022

Fishr: Invariant gradient variances for out-of-distribution generalization
A. Rame, C. Dancette, M. Cord
ICML 2022

Image-to-Lidar self-supervised distillation for autonomous driving data
C. Sautier, G. Puy, S. Gidaris, A. Boulch, A. Bursuc, R. Marlet
CVPR 2022 [code]

POCO: Point convolution for surface reconstruction
A. Boulch, R. Marlet
CVPR 2022 [code]

Raw high-definition radar for multi-task learning
J. Rebut, A. Ouaknine, W. Malik, P. Pérez
CVPR 2022 [data, video]

DyTox: Transformers for continual learning with dynamic token expansion
A. Douillard, A. Ramé, G. Couairon, M. Cord
CVPR 2022

Solving disjunctive temporal networks with uncertainty under restricted time-based controllability using tree search and graph neural networks
K. Osanlou, J. Frank, A. Bursuc, T. Cazenave, E. Jacopin, Ch. Guettier, J. Benton
AAAI 2022

Deep surface reconstruction from point clouds with visibility information
R. Sulzer, L. Landrieu, A. Boulch, R. Marlet, B. Vallet
ICPR 2022

VASAD: a volume and semantic dataset for building reconstruction from point clouds
P.-A. Langlois, Y. Xiao, A. Boulch, R. Marlet
ICPR 2022 [data]

Diverse probabilistic trajectory forecasting with admissibility constraints
L. Calem, H. Ben-Younes, P. Pérez, N. Thome
ICPR 2022

Spherical Perspective on Learning with Normalization Layers
S. Roburin, Y. de Mont-Marin, A. Bursuc, R. Marlet, P. Pérez, M. Aubry
Neurocomputing, 2022

Cross-modal Learning for Domain Adaptation in 3D Semantic Segmentation
M. Jaritz, T.H. Vu, R. de Charette, É. Wirbel, P. Pérez
PAMI, 2022 [code]

Raising context awareness in motion forecasting
H. Ben-Younes, É. Zablocki, M. Chen, P. Pérez, M. Cord
CVPR Workshop on Autonomous Driving (WAD 2022)

CSG0: Continual Urban Scene Generation with Zero Forgetting
H. Jain, T.H. Vu, P. Pérez, M. Cord
CVPR Workshop on Continual Learning (CLVision 2022)

Multi-head distillation for continual unsupervised domain adaptation in semantic segmentation
A. Saporta, A. Douillard, T.H. Vu, P. Pérez, M. Cord
CVPR Workshop on Continual Learning (CLVision 2022) [code]

2021

Driving behavior explanation with multi-level fusion
H. Ben-Younes, É. Zablocki, P. Pérez, M. Cord
Pattern Recognition, 2021 [code]

Localizing Objects with Self-Supervised Transformers and no Labels
O. Siméoni, G. Puy, H. V. Vo, S. Roburin, S. Gidaris, A. Bursuc, P. Pérez, R. Marlet, J. Ponce
BMVC 2021 [code,page]

Generative zero-shot learning for semantic segmentation of 3D point clouds
B. Michele, A. Boulch, G. Puy, R. Marlet, M. Bucher
3DV 2021

NeeDrop: Unsupervised shape representation from sparse point clouds using needle dropping
A. Boulch, G. Puy, R. Marlet
3DV 2021 [code]

PoseContrast: Class-agnostic object viewpoint estimation in the wild with pose-aware contrastive learning
Y. Xiao, Y. Du, R. Marlet
3DV 2021

Large-scale unsupervised object discovery
H.V. Vo, E. Sizikova, C. Schmid, P. Pérez, J. Ponce
NeurIPS 2021

StyleLess layer: Improving robustness for real-world driving
J. Rebut, A. Bursuc, P. Pérez
IROS 2021 [page]

Beyond question-based biases: Assessing multimodal shortcut learning in visual question answering
C. Dancette, R. Cadene, D. Teney, M. Cord
ICCV 2021

MixMo: Mixing multiple inputs for multiple outputs via deep subnetworks
A. Ramé, R. Sun, M. Cord
ICCV 2021

PCAM: Product of Cross-Attention Matrices for Rigid Registration of Point Clouds
A.Q. Cao, G. Puy, A. Boulch, R. Marlet
ICCV 2021 [code,page]

Multi-view radar semantic segmentation
A. Ouaknine, A. Newson, P. Pérez, F. Tupin, J. Rebut
ICCV 2021 [code,page]

Multi-target adversarial frameworks for domain adaptation in in semantic segmentation
A. Saporta, T.H. Vu, M. Cord, P. Pérez
ICCV 2021 [code,page,video]

Triggering Failures: Out-Of-Distribution detection by learning from local adversarial attacks in Semantic Segmentation
V. Besnier, A. Bursuc, D. Picard, A. Briot
ICCV 2021 [code,page]

Handling new target classes in semantic segmentation with domain adaptation
M. Bucher, T.-H. Vu, M. Cord, P. Pérez
Computer Vision and Image Understanding, 2021 [page]

Detecting 32 pedestrian attributes for autonomous vehicles
T. Mordan, M. Cord, P. Pérez, A. Alahi
IEEE Trans. on Intelligent Transportation Systems, 2021 [code]

Confidence estimation via auxiliary models
Ch. Corbière, N. Thome, A. Sapporta, T.H. Vu, P. Pérez, M. Cord
IEEE Trans. PAMI, 2021 [code,page]

Neural monocular 3D human motion capture with physical awareness
S. Shimada, V. Golyanik, W. Xu, P. Pérez, Ch. Theobalt
Siggraph 2021 [page,video]

Semantic Palette: Guiding scene generation with class proportions
G. Le Moing, T.H. Vu, H. Jain, P. Pérez, M. Cord
CVPR 2021 [code,page,video]

Online bag-of-visual-words generation for unsupervised representation learning
S. Gidaris, A. Bursuc, G. Puy, N. Komodakis, M. Cord, P. Pérez
CVPR 2021 [code,page,video]

PLOP: Learning without forgetting for continual semantic segmentation
Arthur Douillard, Yifu Chen, Arnaud Dapogny, Matthieu Cord
CVPR 2021 [code]

Artificial dummies for urban dataset augmentation
A. Vobecký, D. Hurych, M. Uricár, P. Pérez, J. Sivic
AAAI 2021 [code, page, talk]

Scalable surface reconstruction with Delaunay-graph neural networks
R. Sulzer, L. Landrieu, R. Marlet, B. Vallet
CGF 2021

3D reconstruction by parameterized surface mapping
P.-A. Langlois, M. Fisher, O. Wang, V. Kim, A. Boulch, R. Marlet, B. Russell
ICIP 2021

2020

PLOP: Probabilistic poLynomial Objects trajectory Prediction for autonomous driving
Th. Buhet, E. Wirbel, A. Bursuc, X. Perrotton
CoRL 2020 [page]

CARRADA Dataset: Camera and Automotive Radar with Range-Angle-Doppler Annotations
A. Ouaknine, A. Newson, J. Rebut, F. Tupin, P. Pérez
ICPR 2020 [dataset]

STaRFlow: A SpatioTemporal Recurrent Cell for Lightweight Multi-Frame Optical Flow Estimation
P. Godet, A. Boulch, A. Plyer, G. Le Besnerais
ICPR 2020

FKAConv: Feature-Kernel Alignment for Point Cloud Convolution
A. Boulch, G. Puy, R. Marlet
ACCV 2020 [page, code]

QuEST: Quantized Embedding Space for Transferring knowledge
H. Jain, S. Gidaris, N. Komodakis, P. Pérez, M. Cord
ECCV 2020 [page]

Toward unsupervised, multi-object discovery in large-scale image collections
H. V. Vo, P. Pérez, J. Ponce
ECCV 2020 [page, code]

FLOT: Scene Flow estimation by Learned Optimal Transport on point clouds
G. Puy, A. Boulch, R. Marlet
ECCV 2020 [page, code]

Few-shot object detection and viewpoint estimation for objects in the wild
Y. Xiao, R. Marlet
ECCV 2020 [page]

Pixel-Pair Occlusion Relationship Map (P2ORM): Formulation, inference & application
X. Qiu, Y. Xiao, Ch. Wang, R. Marlet
ECCV 2020 [page, code]

TRADI: Tracking deep neural network weight distributions
G. Franchi, A. Bursuc, E. Aldea, S. Dubuisson, I. Bloch
ECCV 2020 [page]

Small-Task Incremental Learning
A. Douillard, M. Cord, Ch. Ollion, Th. Robert, Ed. Valle
ECCV 2020 [code]

Learning representations by predicting bags of visual words
S. Gidaris, A. Bursuc, N. Komodakis, P. Pérez, M. Cord
CVPR 2020 [page]

xMUDA: Cross-Modal Unsupervised Domain Adaptation for 3D semantic segmentation
M. Jaritz, T.H. Vu, R. de Charette, E. Wirbel, P. Pérez
CVPR 2020 [page, code]

End-to-end model-free reinforcement learning for urban driving using implicit affordances
M. Toromanoff, E. Wirbel, F. Moutarde
CVPR 2020 [page, code]

Approximating shapes in images with low-complexity polygons
M. Li, F. Lafarge, R. Marlet
CVPR 2020 [code]

StyleRig: Rigging StyleGAN for 3D control over portrait images
A. Tewari, M. Elgharib, G. Bharaj, F. Bernard, H.P. Seidel, P. Pérez, M. Zollhöfer, Ch. Theobalt
CVPR 2020 [page]

The Missing Data Encoder: Cross-channel image completion with hide-and-seek adversarial network
A. Dapogny, M. Cord, P. Pérez
AAAI 2020 [code]

This dataset does not exist: training models from generated images
V. Besnier, H. Jain, A. Bursuc, M. Cord, P. Pérez
ICASSP 2020 [page]

Dynamic task weighting methods for multi-task networks in autonomous driving systems
I. Leang, G. Sistu, F. Burger, A. Bursuc, S. Yogamani
ITSC 2020 [page]

Deep open space segmentation using automotive radar
F. Nowruzi, D. Kolhatkar, P. Kapoor, F. Al Hassanat, E. Heravi, R. Laganiere, J. Rebut, W. Malik
ICMIM 2020

ConvPoint: continuous convolution for point cloud processing
A. Boulch
Computer and Graphics Journal, 2020 [code]

ESL: Entropy-guided Self-supervised Learning for Domain Adaptation in Semantic Segmentation
A. Saporta, T.H. Vu, M. Cord, P. Pérez
Workshop CVPR 2020 [code]

Driving behavior explanation with multi-level fusion
H. Ben-Younes, É. Zablocki, P. Pérez, M. Cord
Workshop Neurips 2020 [code]

2019

Addressing failure detection by learning model confidence
Ch. Corbière, N. Thome, A. Bar-Hen, M. Cord, P. Pérez
NeurIPS 2019 [page, code]

Zero-Shot Semantic Segmentation
M. Bucher, T.-H. Vu, M. Cord, P. Pérez
NeurIPS 2019 [page, code]

DADA: Depth-aware Domain Adaptation in semantic segmentation
T.-H. Vu, H. Jain, M. Bucher, M. Cord, P. Pérez
ICCV 2019 [page, code]

Boosting few-shot visual learning with self-supervision
S. Gidaris, A. Bursuc, N. Komodakis, P. Pérez, M. Cord
ICCV 2019 [page, code]

WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving
S. Yogamani, C. Hughes, J. Horgan, G. Sistu, P. Varley, D. O’Dea, M. Uricar, S. Milz, M. Simon, K. Amende, Ch. Witt, H. Rashed, S. Chennupati, S. Nayak, S. Mansoor, X. Perroton, P. Pérez
ICCV 2019 [page, dataset]

AdvEnt: Adversarial Entropy minimization for domain adaptation in semantic segmentation
T.-H. Vu, H. Jain, M. Bucher, M. Cord, P. Pérez
CVPR 2019 [page, blog,code]

FML: Face Model Learning from Videos
A. Tewari, F. Bernard, P. Garrido, G. Bharaj, M. Elgharib, H.-P. Seidel, P. Pérez, M. Zollhöfer, Ch. Theobalt
CVPR 2019 [page]

A flexible convolutional solver with application to photorealistic style transfer
G. Puy, P. Pérez
CVPR 2019

Unsupervised image matching and object discovery as optimization
H. V. Vo, F. Bach, M. Cho, K. Han, Y. LeCun, P. Pérez, J. Ponce
CVPR 2019 [page, code]

SoDeep: a Sorting Deep net to learn ranking loss surrogates
M. Engilberge, L. Chevallier, M. Cord, P. Pérez
CVPR 2019 [code]

Dense classification and implanting for few-shot learning
Y. Lifchitz, Y. Avrithis, S. Picard, A. Bursuc
CVPR 2019

Generating classification weights with gnn denoising autoencoders for few-shot learning
S. Gidaris, N. Komodakis
CVPR 2019 [code]

Optimal solving of constrained path-planning problems with graph convolutional networks and optimized tree search
K. Osanlou, A. Bursuc, Ch. Guettier, T. Cazenave, E. Jacopin
IROS 2019

Surface Reconstruction from 3D Line Segments
P.-A. Langlois, A. Boulch, R. Marlet
3DV 2019

Advanced Pedestrian Dataset Augmentation for Autonomous Driving
A. Vobecky, M. Uricár, D. Hurych, R. Skoviera
Workshop ICCV 2019

Adversarial frontier stitching for remote neural network watermarking
E. Le Merrer, P. Pérez, G. Trédan
Neural Computing and Applications, 2019

Weakly supervised representation learning for audio-visual scene analysis
S. Parekh, S. Essid, A. Ozerov, N. QK Duong, P. Pérez, G. Richard
IEEE Trans. Audio, Speech and Language Proc. (T-ASLP), 2019 [page]

Understanding and improving kernel local descriptors
A. Mukundan, G. Tolias, A. Bursuc, H. Jégou, O. Chum
Int. J. Computer Vision (IJCV), 2019