no code implementations • 27 Jun 2023 • Chris Zhang, Runsheng Guo, Wenyuan Zeng, Yuwen Xiong, Binbin Dai, Rui Hu, Mengye Ren, Raquel Urtasun
Recent advances in high-fidelity simulators have enabled closed-loop training of autonomous driving agents, potentially solving the distribution shift in training v. s.
no code implementations • 17 Dec 2021 • Dingwen Zhang, Wenyuan Zeng, Guangyu Guo, Chaowei Fang, Lechao Cheng, Ming-Ming Cheng, Junwei Han
Current weakly supervised semantic segmentation (WSSS) frameworks usually contain the separated mask-refinement model and the main semantic region mining model.
Knowledge Distillation Weakly supervised Semantic Segmentation +1
no code implementations • 8 Apr 2021 • Sean Segal, Nishanth Kumar, Sergio Casas, Wenyuan Zeng, Mengye Ren, Jingkang Wang, Raquel Urtasun
As data collection is often significantly cheaper than labeling in this domain, the decision of which subset of examples to label can have a profound impact on model performance.
no code implementations • 18 Jan 2021 • Jerry Liu, Wenyuan Zeng, Raquel Urtasun, Ersin Yumer
An intelligent agent operating in the real-world must balance achieving its goal with maintaining the safety and comfort of not only itself, but also other participants within the surrounding scene.
1 code implementation • CVPR 2019 • Wenyuan Zeng, Wenjie Luo, Simon Suo, Abbas Sadat, Bin Yang, Sergio Casas, Raquel Urtasun
In this paper, we propose a neural motion planner (NMP) for learning to drive autonomously in complex urban scenarios that include traffic-light handling, yielding, and interactions with multiple road-users.
no code implementations • 17 Jan 2021 • Wenyuan Zeng, Ming Liang, Renjie Liao, Raquel Urtasun
In this paper, we propose LaneRCNN, a graph-centric motion forecasting model.
Ranked #150 on Motion Forecasting on Argoverse CVPR 2020
no code implementations • 17 Jan 2021 • Wenyuan Zeng, Yuwen Xiong, Raquel Urtasun
This process is typically time-consuming and requires expert knowledge to achieve good results.
no code implementations • 17 Jan 2021 • Bin Yang, Min Bai, Ming Liang, Wenyuan Zeng, Raquel Urtasun
The key idea is to decompose the 4D object label into two parts: the object size in 3D that's fixed through time for rigid objects, and the motion path describing the evolution of the object's pose through time.
no code implementations • ICCV 2021 • Yuwen Xiong, Mengye Ren, Wenyuan Zeng, Raquel Urtasun
Motivated by this ability, we present a new self-supervised learning representation framework that can be directly deployed on a video stream of complex scenes with many moving objects.
no code implementations • 7 Jan 2021 • Katie Luo, Sergio Casas, Renjie Liao, Xinchen Yan, Yuwen Xiong, Wenyuan Zeng, Raquel Urtasun
On two large-scale real-world datasets, nuScenes and ATG4D, we showcase that our scene-occupancy predictions are more accurate and better calibrated than those from state-of-the-art motion forecasting methods, while also matching their performance in pedestrian motion forecasting metrics.
no code implementations • 2 Nov 2020 • Bob Wei, Mengye Ren, Wenyuan Zeng, Ming Liang, Bin Yang, Raquel Urtasun
In this paper, we propose an end-to-end self-driving network featuring a sparse attention module that learns to automatically attend to important regions of the input.
1 code implementation • CVPR 2021 • Julieta Martinez, Jashan Shewakramani, Ting Wei Liu, Ioan Andrei Bârsan, Wenyuan Zeng, Raquel Urtasun
Compressing large neural networks is an important step for their deployment in resource-constrained computational platforms.
no code implementations • ECCV 2020 • Jiayuan Gu, Wei-Chiu Ma, Sivabalan Manivasagam, Wenyuan Zeng, ZiHao Wang, Yuwen Xiong, Hao Su, Raquel Urtasun
3D shape completion for real data is important but challenging, since partial point clouds acquired by real-world sensors are usually sparse, noisy and unaligned.
3 code implementations • ECCV 2020 • Tsun-Hsuan Wang, Sivabalan Manivasagam, Ming Liang, Bin Yang, Wenyuan Zeng, James Tu, Raquel Urtasun
In this paper, we explore the use of vehicle-to-vehicle (V2V) communication to improve the perception and motion forecasting performance of self-driving vehicles.
Ranked #1 on 3D Object Detection on OPV2V
no code implementations • ECCV 2020 • Wenyuan Zeng, Shenlong Wang, Renjie Liao, Yun Chen, Bin Yang, Raquel Urtasun
In this paper, we propose the Deep Structured self-Driving Network (DSDNet), which performs object detection, motion prediction, and motion planning with a single neural network.
no code implementations • 13 Aug 2020 • Lingyun Luke Li, Bin Yang, Ming Liang, Wenyuan Zeng, Mengye Ren, Sean Segal, Raquel Urtasun
We show that our approach can outperform the state-of-the-art on both datasets.
no code implementations • CVPR 2020 • Sivabalan Manivasagam, Shenlong Wang, Kelvin Wong, Wenyuan Zeng, Mikita Sazanovich, Shuhan Tan, Bin Yang, Wei-Chiu Ma, Raquel Urtasun
We first utilize ray casting over the 3D scene and then use a deep neural network to produce deviations from the physics-based simulation, producing realistic LiDAR point clouds.
no code implementations • CVPR 2020 • Ming Liang, Bin Yang, Wenyuan Zeng, Yun Chen, Rui Hu, Sergio Casas, Raquel Urtasun
We tackle the problem of joint perception and motion forecasting in the context of self-driving vehicles.
no code implementations • 27 Sep 2018 • Wenyuan Zeng, Raquel Urtasun
Model compression can significantly reduce the computation and memory footprint of large neural networks.
4 code implementations • ICML 2018 • Shengyang Sun, Guodong Zhang, Chaoqi Wang, Wenyuan Zeng, Jiaman Li, Roger Grosse
The NKN architecture is based on the composition rules for kernels, so that each unit of the network corresponds to a valid kernel.
9 code implementations • ICML 2018 • Mengye Ren, Wenyuan Zeng, Bin Yang, Raquel Urtasun
Deep neural networks have been shown to be very powerful modeling tools for many supervised learning tasks involving complex input patterns.
no code implementations • 10 Nov 2016 • Wenyuan Zeng, Wenjie Luo, Sanja Fidler, Raquel Urtasun
Towards this goal, we first introduce a simple mechanism that first reads the input sequence before committing to a representation of each word.
1 code implementation • EMNLP 2017 • Wenyuan Zeng, Yankai Lin, Zhiyuan Liu, Maosong Sun
Distantly supervised relation extraction has been widely used to find novel relational facts from plain text.