Search Results for author: Patrick Pérez

Found 54 papers, 25 papers with code

STEEX: Steering Counterfactual Explanations with Semantics

no code implementations17 Nov 2021 Paul Jacob, Éloi Zablocki, Hédi Ben-Younes, Mickaël Chen, Patrick Pérez, Matthieu Cord

As deep learning models are increasingly used in safety-critical applications, explainability and trustworthiness become major concerns.

Counterfactual Explanation

Localizing Objects with Self-Supervised Transformers and no Labels

1 code implementation29 Sep 2021 Oriane Siméoni, Gilles Puy, Huy V. Vo, Simon Roburin, Spyros Gidaris, Andrei Bursuc, Patrick Pérez, Renaud Marlet, Jean Ponce

We also show that training a class-agnostic detector on the discovered objects boosts results by another 7 points.

Object Discovery

Raising context awareness in motion forecasting

no code implementations16 Sep 2021 Hédi Ben-Younes, Éloi Zablocki, Mickaël Chen, Patrick Pérez, Matthieu Cord

Learning-based trajectory prediction models have encountered great success, with the promise of leveraging contextual information in addition to motion history.

Motion Forecasting Trajectory Prediction

LiDARTouch: Monocular metric depth estimation with a few-beam LiDAR

no code implementations8 Sep 2021 Florent Bartoccioni, Éloi Zablocki, Patrick Pérez, Matthieu Cord, Karteek Alahari

In such a monocular setup, dense depth is obtained with either additional input from one or several expensive LiDARs, e. g., with 64 beams, or camera-only methods, which suffer from scale-ambiguity and infinite-depth problems.

Depth Completion Depth Estimation

Multi-Target Adversarial Frameworks for Domain Adaptation in Semantic Segmentation

1 code implementation ICCV 2021 Antoine Saporta, Tuan-Hung Vu, Matthieu Cord, Patrick Pérez

In this work, we address the task of unsupervised domain adaptation (UDA) for semantic segmentation in presence of multiple target domains: The objective is to train a single model that can handle all these domains at test time.

Semantic Segmentation Transfer Learning +1

Large-Scale Unsupervised Object Discovery

1 code implementation NeurIPS 2021 Huy V. Vo, Elena Sizikova, Cordelia Schmid, Patrick Pérez, Jean Ponce

Extensive experiments on COCO and OpenImages show that, in the single-object discovery setting where a single prominent object is sought in each image, the proposed LOD (Large-scale Object Discovery) approach is on par with, or better than the state of the art for medium-scale datasets (up to 120K images), and over 37% better than the only other algorithms capable of scaling up to 1. 7M images.

Multi-object discovery Object Discovery +1

Semantic Palette: Guiding Scene Generation with Class Proportions

1 code implementation CVPR 2021 Guillaume Le Moing, Tuan-Hung Vu, Himalaya Jain, Patrick Pérez, Matthieu Cord

Despite the recent progress of generative adversarial networks (GANs) at synthesizing photo-realistic images, producing complex urban scenes remains a challenging problem.

Data Augmentation Image Generation +1

Neural Monocular 3D Human Motion Capture with Physical Awareness

no code implementations3 May 2021 Soshi Shimada, Vladislav Golyanik, Weipeng Xu, Patrick Pérez, Christian Theobalt

We present a new trainable system for physically plausible markerless 3D human motion capture, which achieves state-of-the-art results in a broad range of challenging scenarios.

3D Pose Estimation Motion Capture

StyleLess layer: Improving robustness for real-world driving

no code implementations25 Mar 2021 Julien Rebut, Andrei Bursuc, Patrick Pérez

Robustness to various image corruptions, caused by changing weather conditions or sensor degradation and aging, is crucial for safety when such vehicles are deployed in the real world.

Autonomous Driving Semantic Segmentation

OBoW: Online Bag-of-Visual-Words Generation for Self-Supervised Learning

2 code implementations CVPR 2021 Spyros Gidaris, Andrei Bursuc, Gilles Puy, Nikos Komodakis, Matthieu Cord, Patrick Pérez

With this in mind, we propose a teacher-student scheme to learn representations by training a convolutional net to reconstruct a bag-of-visual-words (BoW) representation of an image, given as input a perturbed version of that same image.

Object Detection Self-Supervised Image Classification +4

Artificial Dummies for Urban Dataset Augmentation

1 code implementation15 Dec 2020 Antonín Vobecký, David Hurych, Michal Uřičář, Patrick Pérez, Josef Šivic

This is achieved with a data generator (called DummyNet) with disentangled control of the pose, the appearance, and the target background scene.

Autonomous Driving

Confidence Estimation via Auxiliary Models

no code implementations11 Dec 2020 Charles Corbière, Nicolas Thome, Antoine Saporta, Tuan-Hung Vu, Matthieu Cord, Patrick Pérez

In this paper, we introduce a novel target criterion for model confidence, namely the true class probability (TCP).

Domain Adaptation Image Classification +1

Driving Behavior Explanation with Multi-level Fusion

1 code implementation9 Dec 2020 Hédi Ben-Younes, Éloi Zablocki, Patrick Pérez, Matthieu Cord

In this era of active development of autonomous vehicles, it becomes crucial to provide driving systems with the capacity to explain their decisions.

Explainable artificial intelligence Trajectory Prediction

Detecting 32 Pedestrian Attributes for Autonomous Vehicles

1 code implementation4 Dec 2020 Taylor Mordan, Matthieu Cord, Patrick Pérez, Alexandre Alahi

By increasing the number of attributes jointly learned, we highlight an issue related to the scales of gradients, which arises in MTL with numerous tasks.

Autonomous Driving Multi-Task Learning

PIE: Portrait Image Embedding for Semantic Control

no code implementations20 Sep 2020 Ayush Tewari, Mohamed Elgharib, Mallikarjun B R., Florian Bernard, Hans-Peter Seidel, Patrick Pérez, Michael Zollhöfer, Christian Theobalt

We present the first approach for embedding real portrait images in the latent space of StyleGAN, which allows for intuitive editing of the head pose, facial expression, and scene illumination in the image.

Face Model

VRUNet: Multi-Task Learning Model for Intent Prediction of Vulnerable Road Users

no code implementations10 Jul 2020 Adithya Ranga, Filippo Giruzzi, Jagdish Bhanushali, Emilie Wirbel, Patrick Pérez, Tuan-Hung Vu, Xavier Perrotton

In this paper we propose a multi-task learning model to predict pedestrian actions, crossing intent and forecast their future path from video sequences.

Autonomous Vehicles Motion Planning +1

ESL: Entropy-guided Self-supervised Learning for Domain Adaptation in Semantic Segmentation

1 code implementation15 Jun 2020 Antoine Saporta, Tuan-Hung Vu, Matthieu Cord, Patrick Pérez

While fully-supervised deep learning yields good models for urban scene semantic segmentation, these models struggle to generalize to new environments with different lighting or weather conditions for instance.

Self-Supervised Learning Semantic Segmentation +1

Photo style transfer with consistency losses

no code implementations9 May 2020 Xu Yao, Gilles Puy, Patrick Pérez

We address the problem of style transfer between two photos and propose a new way to preserve photorealism.

Style Transfer

Handling new target classes in semantic segmentation with domain adaptation

1 code implementation2 Apr 2020 Maxime Bucher, Tuan-Hung Vu, Matthieu Cord, Patrick Pérez

In this work, we define and address a novel domain adaptation (DA) problem in semantic scene segmentation, where the target domain not only exhibits a data distribution shift w. r. t.

Scene Segmentation Universal Domain Adaptation +2

StyleRig: Rigging StyleGAN for 3D Control over Portrait Images

no code implementations CVPR 2020 Ayush Tewari, Mohamed Elgharib, Gaurav Bharaj, Florian Bernard, Hans-Peter Seidel, Patrick Pérez, Michael Zollhöfer, Christian Theobalt

StyleGAN generates photorealistic portrait images of faces with eyes, teeth, hair and context (neck, shoulders, background), but lacks a rig-like control over semantic face parameters that are interpretable in 3D, such as face pose, expressions, and scene illumination.

Learning Representations by Predicting Bags of Visual Words

1 code implementation CVPR 2020 Spyros Gidaris, Andrei Bursuc, Nikos Komodakis, Patrick Pérez, Matthieu Cord

Inspired by the success of NLP methods in this area, in this work we propose a self-supervised approach based on spatially dense image descriptions that encode discrete visual concepts, here called visual words.

Representation Learning

Deep Reinforcement Learning for Autonomous Driving: A Survey

no code implementations2 Feb 2020 B Ravi Kiran, Ibrahim Sobh, Victor Talpaert, Patrick Mannion, Ahmad A. Al Sallab, Senthil Yogamani, Patrick Pérez

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.

Autonomous Driving Imitation Learning +1

Scattering Features for Multimodal Gait Recognition

no code implementations23 Jan 2020 Srđan Kitić, Gilles Puy, Patrick Pérez, Philippe Gilberton

We consider the problem of identifying people on the basis of their walk (gait) pattern.

Gait Recognition

QUEST: Quantized embedding space for transferring knowledge

1 code implementation ECCV 2020 Himalaya Jain, Spyros Gidaris, Nikos Komodakis, Patrick Pérez, Matthieu Cord

Knowledge distillation refers to the process of training a compact student network to achieve better accuracy by learning from a high capacity teacher network.

Knowledge Distillation

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

1 code implementation CVPR 2020 Maximilian Jaritz, Tuan-Hung Vu, Raoul de Charette, Émilie Wirbel, Patrick Pérez

In this work, we explore how to learn from multi-modality and propose cross-modal UDA (xMUDA) where we assume the presence of 2D images and 3D point clouds for 3D semantic segmentation.

3D Semantic Segmentation Autonomous Driving +1

This dataset does not exist: training models from generated images

no code implementations7 Nov 2019 Victor Besnier, Himalaya Jain, Andrei Bursuc, Matthieu Cord, Patrick Pérez

This naturally brings the question: Can we train a classifier only on the generated data?

Boosting Few-Shot Visual Learning with Self-Supervision

1 code implementation ICCV 2019 Spyros Gidaris, Andrei Bursuc, Nikos Komodakis, Patrick Pérez, Matthieu Cord

Few-shot learning and self-supervised learning address different facets of the same problem: how to train a model with little or no labeled data.

Few-Shot Learning Self-Supervised Learning

FML: Face Model Learning from Videos

no code implementations CVPR 2019 Ayush Tewari, Florian Bernard, Pablo Garrido, Gaurav Bharaj, Mohamed Elgharib, Hans-Peter Seidel, Patrick Pérez, Michael Zollhöfer, Christian Theobalt

In contrast, we propose multi-frame video-based self-supervised training of a deep network that (i) learns a face identity model both in shape and appearance while (ii) jointly learning to reconstruct 3D faces.

3D Reconstruction Face Model

A Flexible Convolutional Solver with Application to Photorealistic Style Transfer

no code implementations13 Jun 2018 Gilles Puy, Patrick Pérez

In contrast to existing convnets that address the same task, our architecture derives directly from the structure of the gradient descent originally used to solve the style transfer problem [Gatys et al., 2016].

Style Transfer

Deep Video Portraits

no code implementations29 May 2018 Hyeongwoo Kim, Pablo Garrido, Ayush Tewari, Weipeng Xu, Justus Thies, Matthias Nießner, Patrick Pérez, Christian Richardt, Michael Zollhöfer, Christian Theobalt

In order to enable source-to-target video re-animation, we render a synthetic target video with the reconstructed head animation parameters from a source video, and feed it into the trained network -- thus taking full control of the target.

Face Model

Weakly Supervised Representation Learning for Unsynchronized Audio-Visual Events

no code implementations19 Apr 2018 Sanjeel Parekh, Slim Essid, Alexey Ozerov, Ngoc Q. K. Duong, Patrick Pérez, Gaël Richard

Audio-visual representation learning is an important task from the perspective of designing machines with the ability to understand complex events.

Multiple Instance Learning Representation Learning

Finding beans in burgers: Deep semantic-visual embedding with localization

1 code implementation CVPR 2018 Martin Engilberge, Louis Chevallier, Patrick Pérez, Matthieu Cord

Several works have proposed to learn a two-path neural network that maps images and texts, respectively, to a same shared Euclidean space where geometry captures useful semantic relationships.

Cross-Modal Retrieval Image Captioning +1

Learning a Complete Image Indexing Pipeline

no code implementations CVPR 2018 Himalaya Jain, Joaquin Zepeda, Patrick Pérez, Rémi Gribonval

To work at scale, a complete image indexing system comprises two components: An inverted file index to restrict the actual search to only a subset that should contain most of the items relevant to the query; An approximate distance computation mechanism to rapidly scan these lists.

Self-supervised Multi-level Face Model Learning for Monocular Reconstruction at over 250 Hz

no code implementations CVPR 2018 Ayush Tewari, Michael Zollhöfer, Pablo Garrido, Florian Bernard, Hyeongwoo Kim, Patrick Pérez, Christian Theobalt

To alleviate this problem, we present the first approach that jointly learns 1) a regressor for face shape, expression, reflectance and illumination on the basis of 2) a concurrently learned parametric face model.

Face Model

Audio style transfer

1 code implementation31 Oct 2017 Eric Grinstein, Ngoc Duong, Alexey Ozerov, Patrick Pérez

"Style transfer" among images has recently emerged as a very active research topic, fuelled by the power of convolution neural networks (CNNs), and has become fast a very popular technology in social media.

Sound Audio and Speech Processing Classical Physics

MoFA: Model-based Deep Convolutional Face Autoencoder for Unsupervised Monocular Reconstruction

no code implementations ICCV 2017 Ayush Tewari, Michael Zollhöfer, Hyeongwoo Kim, Pablo Garrido, Florian Bernard, Patrick Pérez, Christian Theobalt

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.

Face Reconstruction

Unifying local and non-local signal processing with graph CNNs

no code implementations24 Feb 2017 Gilles Puy, Srdan Kitic, Patrick Pérez

This paper deals with the unification of local and non-local signal processing on graphs within a single convolutional neural network (CNN) framework.

Style Transfer

ROAM: a Rich Object Appearance Model with Application to Rotoscoping

no code implementations CVPR 2017 Ondrej Miksik, Juan-Manuel Pérez-Rúa, Philip H. S. Torr, Patrick Pérez

Rotoscoping, the detailed delineation of scene elements through a video shot, is a painstaking task of tremendous importance in professional post-production pipelines.

Approximate search with quantized sparse representations

no code implementations10 Aug 2016 Himalaya Jain, Patrick Pérez, Rémi Gribonval, Joaquin Zepeda, Hervé Jégou

This paper tackles the task of storing a large collection of vectors, such as visual descriptors, and of searching in it.


Sketching for Large-Scale Learning of Mixture Models

no code implementations9 Jun 2016 Nicolas Keriven, Anthony Bourrier, Rémi Gribonval, Patrick Pérez

We propose a "compressive learning" framework where we estimate model parameters from a sketch of the training data.

Compressive Sensing Speaker Verification

Video Inpainting of Complex Scenes

no code implementations18 Mar 2015 Alasdair Newson, Andrés Almansa, Matthieu Fradet, Yann Gousseau, Patrick Pérez

Our algorithm is able to deal with a variety of challenging situations which naturally arise in video inpainting, such as the correct reconstruction of dynamic textures, multiple moving objects and moving background.

Image Inpainting Video Editing +1

Cannot find the paper you are looking for? You can Submit a new open access paper.