107 citations · 243 across the 14 of their papers we have counts for
19 papers
STEEX: Steering Counterfactual Explanations with Semantics
Paul Jacob, Éloi Zablocki, Hédi Ben-Younes +3
As deep learning models are increasingly used in safety-critical applications, explainability and trustworthiness become major concerns. For simple images, such as low-resolution f…
Localizing Objects with Self-Supervised Transformers and no Labels
Oriane Siméoni, Gilles Puy, Huy V. Vo +6
Localizing objects in image collections without supervision can help to avoid expensive annotation campaigns. We propose a simple approach to this problem, that leverages the activ…
Multi-Target Adversarial Frameworks for Domain Adaptation in Semantic Segmentation
Antoine Saporta, Tuan-Hung Vu, Matthieu Cord +1
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…
LiDARTouch: Monocular metric depth estimation with a few-beam LiDAR
Florent Bartoccioni, Éloi Zablocki, Patrick Pérez +2
Vision-based depth estimation is a key feature in autonomous systems, which often relies on a single camera or several independent ones. In such a monocular setup, dense depth is o…
Semantic Palette: Guiding Scene Generation with Class Proportions
Guillaume Le Moing, Tuan-Hung Vu, Himalaya Jain +2
Despite the recent progress of generative adversarial networks (GANs) at synthesizing photo-realistic images, producing complex urban scenes remains a challenging problem. Previous…
Large-Scale Unsupervised Object Discovery
Huy V. Vo, Elena Sizikova, Cordelia Schmid +2
Existing approaches to unsupervised object discovery (UOD) do not scale up to large datasets without approximations that compromise their performance. We propose a novel formulatio…
Neural Monocular 3D Human Motion Capture with Physical Awareness
Soshi Shimada, Vladislav Golyanik, Weipeng Xu +2
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. Un…
StyleLess layer: Improving robustness for real-world driving
Julien Rebut, Andrei Bursuc, Patrick Pérez
Deep Neural Networks (DNNs) are a critical component for self-driving vehicles. They achieve impressive performance by reaping information from high amounts of labeled data. Yet, t…
Multi-View Radar Semantic Segmentation
Arthur Ouaknine, Alasdair Newson, Patrick Pérez +2
Understanding the scene around the ego-vehicle is key to assisted and autonomous driving. Nowadays, this is mostly conducted using cameras and laser scanners, despite their reduced…
Confidence Estimation via Auxiliary Models
Charles Corbière, Nicolas Thome, Antoine Saporta +3
Reliably quantifying the confidence of deep neural classifiers is a challenging yet fundamental requirement for deploying such models in safety-critical applications. In this paper…
Detecting 32 Pedestrian Attributes for Autonomous Vehicles
Taylor Mordan, Matthieu Cord, Patrick Pérez +1
Pedestrians are arguably one of the most safety-critical road users to consider for autonomous vehicles in urban areas. In this paper, we address the problem of jointly detecting p…
Toward unsupervised, multi-object discovery in large-scale image collections
Huy V. Vo, Patrick Pérez, Jean Ponce
This paper addresses the problem of discovering the objects present in a collection of images without any supervision. We build on the optimization approach of Vo et al. (CVPR'19)…
VRUNet: Multi-Task Learning Model for Intent Prediction of Vulnerable Road Users
Adithya Ranga, Filippo Giruzzi, Jagdish Bhanushali +4
Advanced perception and path planning are at the core for any self-driving vehicle. Autonomous vehicles need to understand the scene and intentions of other road users for safe mot…
ESL: Entropy-guided Self-supervised Learning for Domain Adaptation in Semantic Segmentation
Antoine Saporta, Tuan-Hung Vu, Matthieu Cord +1
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 we…
Handling new target classes in semantic segmentation with domain adaptation
Maxime Bucher, Tuan-Hung Vu, Matthieu Cord +1
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…
Learning Representations by Predicting Bags of Visual Words
Spyros Gidaris, Andrei Bursuc, Nikos Komodakis +2
Self-supervised representation learning targets to learn convnet-based image representations from unlabeled data. Inspired by the success of NLP methods in this area, in this work…
Deep Reinforcement Learning for Autonomous Driving: A Survey
B Ravi Kiran, Ibrahim Sobh, Victor Talpaert +4
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…
QUEST: Quantized embedding space for transferring knowledge
Himalaya Jain, Spyros Gidaris, Nikos Komodakis +2
Knowledge distillation refers to the process of training a compact student network to achieve better accuracy by learning from a high capacity teacher network. Most of the existing…
This dataset does not exist: training models from generated images
Victor Besnier, Himalaya Jain, Andrei Bursuc +2
Current generative networks are increasingly proficient in generating high-resolution realistic images. These generative networks, especially the conditional ones, can potentially…