Zobrazeno 1 - 10
of 31
pro vyhledávání: '"Zablocki, Eloi"'
Motion forecasting (MF) for autonomous driving aims at anticipating trajectories of surrounding agents in complex urban scenarios. In this work, we investigate a mixed strategy in MF training that first pre-train motion forecasters on pseudo-labeled
Externí odkaz:
http://arxiv.org/abs/2412.06491
Autor:
Zablocki, Éloi, Gerard, Valentin, Cardiel, Amaia, Gaussier, Eric, Cord, Matthieu, Valle, Eduardo
Understanding deep models is crucial for deploying them in safety-critical applications. We introduce GIFT, a framework for deriving post-hoc, global, interpretable, and faithful textual explanations for vision classifiers. GIFT starts from local fai
Externí odkaz:
http://arxiv.org/abs/2411.15605
Vision Language Models (VLMs) have demonstrated remarkable capabilities in various open-vocabulary tasks, yet their zero-shot performance lags behind task-specific finetuned models, particularly in complex tasks like Referring Expression Comprehensio
Externí odkaz:
http://arxiv.org/abs/2409.11919
In autonomous driving, motion prediction aims at forecasting the future trajectories of nearby agents, helping the ego vehicle to anticipate behaviors and drive safely. A key challenge is generating a diverse set of future predictions, commonly addre
Externí odkaz:
http://arxiv.org/abs/2409.11172
Machine learning based autonomous driving systems often face challenges with safety-critical scenarios that are rare in real-world data, hindering their large-scale deployment. While increasing real-world training data coverage could address this iss
Externí odkaz:
http://arxiv.org/abs/2409.07830
Autor:
Xu, Yihong, Zablocki, Éloi, Boulch, Alexandre, Puy, Gilles, Chen, Mickael, Bartoccioni, Florent, Samet, Nermin, Siméoni, Oriane, Gidaris, Spyros, Vu, Tuan-Hung, Bursuc, Andrei, Valle, Eduardo, Marlet, Renaud, Cord, Matthieu
Motion forecasting is crucial in autonomous driving systems to anticipate the future trajectories of surrounding agents such as pedestrians, vehicles, and traffic signals. In end-to-end forecasting, the model must jointly detect and track from sensor
Externí odkaz:
http://arxiv.org/abs/2406.08113
Autor:
Feng, Lan, Bahari, Mohammadhossein, Amor, Kaouther Messaoud Ben, Zablocki, Éloi, Cord, Matthieu, Alahi, Alexandre
Vehicle trajectory prediction has increasingly relied on data-driven solutions, but their ability to scale to different data domains and the impact of larger dataset sizes on their generalization remain under-explored. While these questions can be st
Externí odkaz:
http://arxiv.org/abs/2403.15098
Autor:
Chambon, Loick, Zablocki, Eloi, Chen, Mickael, Bartoccioni, Florent, Perez, Patrick, Cord, Matthieu
Bird's-eye View (BeV) representations have emerged as the de-facto shared space in driving applications, offering a unified space for sensor data fusion and supporting various downstream tasks. However, conventional models use grids with fixed resolu
Externí odkaz:
http://arxiv.org/abs/2312.00703
The recent enthusiasm for open-world vision systems show the high interest of the community to perform perception tasks outside of the closed-vocabulary benchmark setups which have been so popular until now. Being able to discover objects in images/v
Externí odkaz:
http://arxiv.org/abs/2310.12904
Towards Motion Forecasting with Real-World Perception Inputs: Are End-to-End Approaches Competitive?
Autor:
Xu, Yihong, Chambon, Loïck, Zablocki, Éloi, Chen, Mickaël, Alahi, Alexandre, Cord, Matthieu, Pérez, Patrick
Motion forecasting is crucial in enabling autonomous vehicles to anticipate the future trajectories of surrounding agents. To do so, it requires solving mapping, detection, tracking, and then forecasting problems, in a multi-step pipeline. In this co
Externí odkaz:
http://arxiv.org/abs/2306.09281