429 citations · 608 across the 22 of their papers we have counts for
24 papers
Towards Unsupervised Object Detection From LiDAR Point Clouds
Lunjun Zhang, Anqi Joyce Yang, Yuwen Xiong +4
In this paper, we study the problem of unsupervised object detection from 3D point clouds in self-driving scenes. We present a simple yet effective method that exploits (i) point c…
UltraLiDAR: Learning Compact Representations for LiDAR Completion and Generation
Yuwen Xiong, Wei-Chiu Ma, Jingkang Wang +1
LiDAR provides accurate geometric measurements of the 3D world. Unfortunately, dense LiDARs are very expensive and the point clouds captured by low-beam LiDAR are often sparse. To…
Adv3D: Generating Safety-Critical 3D Objects through Closed-Loop Simulation
Jay Sarva, Jingkang Wang, James Tu +3
Self-driving vehicles (SDVs) must be rigorously tested on a wide range of scenarios to ensure safe deployment. The industry typically relies on closed-loop simulation to evaluate h…
LabelFormer: Object Trajectory Refinement for Offboard Perception from LiDAR Point Clouds
Anqi Joyce Yang, Sergio Casas, Nikita Dvornik +5
A major bottleneck to scaling-up training of self-driving perception systems are the human annotations required for supervision. A promising alternative is to leverage "auto-labell…
Copilot4D: Learning Unsupervised World Models for Autonomous Driving via Discrete Diffusion
Lunjun Zhang, Yuwen Xiong, Ze Yang +3
Learning world models can teach an agent how the world works in an unsupervised manner. Even though it can be viewed as a special case of sequence modeling, progress for scaling wo…
Rethinking Closed-loop Training for Autonomous Driving
Chris Zhang, Runsheng Guo, Wenyuan Zeng +5
Recent advances in high-fidelity simulators have enabled closed-loop training of autonomous driving agents, potentially solving the distribution shift in training v.s. deployment a…
Network Automatic Pruning: Start NAP and Take a Nap
Wenyuan Zeng, Yuwen Xiong, Raquel Urtasun
Network pruning can significantly reduce the computation and memory footprint of large neural networks. To achieve a good trade-off between model size and performance, popular prun…
Cost-Efficient Online Hyperparameter Optimization
Jingkang Wang, Mengye Ren, Ilija Bogunovic +2
Recent work on hyperparameters optimization (HPO) has shown the possibility of training certain hyperparameters together with regular parameters. However, these online HPO algorith…
Safety-Oriented Pedestrian Motion and Scene Occupancy Forecasting
Katie Luo, Sergio Casas, Renjie Liao +4
In this paper, we address the important problem in self-driving of forecasting multi-pedestrian motion and their shared scene occupancy map, critical for safe navigation. Our contr…
Self-Supervised Representation Learning from Flow Equivariance
Yuwen Xiong, Mengye Ren, Wenyuan Zeng +1
Self-supervised representation learning is able to learn semantically meaningful features; however, much of its recent success relies on multiple crops of an image with very few ob…
Weakly-supervised 3D Shape Completion in the Wild
Jiayuan Gu, Wei-Chiu Ma, Sivabalan Manivasagam +5
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. Different from pr…
LoCo: Local Contrastive Representation Learning
Yuwen Xiong, Mengye Ren, Raquel Urtasun
Deep neural nets typically perform end-to-end backpropagation to learn the weights, a procedure that creates synchronization constraints in the weight update step across layers and…
LevelSet R-CNN: A Deep Variational Method for Instance Segmentation
Namdar Homayounfar, Yuwen Xiong, Justin Liang +2
Obtaining precise instance segmentation masks is of high importance in many modern applications such as robotic manipulation and autonomous driving. Currently, many state of the ar…
PolyTransform: Deep Polygon Transformer for Instance Segmentation
Justin Liang, Namdar Homayounfar, Wei-Chiu Ma +3
In this paper, we propose PolyTransform, a novel instance segmentation algorithm that produces precise, geometry-preserving masks by combining the strengths of prevailing segmentat…
Discrete Residual Flow for Probabilistic Pedestrian Behavior Prediction
Ajay Jain, Sergio Casas, Renjie Liao +4
Self-driving vehicles plan around both static and dynamic objects, applying predictive models of behavior to estimate future locations of the objects in the environment. However, f…
Learning to Remember from a Multi-Task Teacher
Yuwen Xiong, Mengye Ren, Raquel Urtasun
Recent studies on catastrophic forgetting during sequential learning typically focus on fixing the accuracy of the predictions for a previously learned task. In this paper we argue…
DMM-Net: Differentiable Mask-Matching Network for Video Object Segmentation
Xiaohui Zeng, Renjie Liao, Li Gu +3
In this paper, we propose the differentiable mask-matching network (DMM-Net) for solving the video object segmentation problem where the initial object masks are provided. Relying…
Deformable Filter Convolution for Point Cloud Reasoning
Yuwen Xiong, Mengye Ren, Renjie Liao +2
Point clouds are the native output of many real-world 3D sensors. To borrow the success of 2D convolutional network architectures, a majority of popular 3D perception models voxeli…
Deep Rigid Instance Scene Flow
Wei-Chiu Ma, Shenlong Wang, Rui Hu +2
In this paper we tackle the problem of scene flow estimation in the context of self-driving. We leverage deep learning techniques as well as strong priors as in our application dom…
UPSNet: A Unified Panoptic Segmentation Network
Yuwen Xiong, Renjie Liao, Hengshuang Zhao +4
In this paper, we propose a unified panoptic segmentation network (UPSNet) for tackling the newly proposed panoptic segmentation task. On top of a single backbone residual network,…
Inference in Probabilistic Graphical Models by Graph Neural Networks
KiJung Yoon, Renjie Liao, Yuwen Xiong +5
A fundamental computation for statistical inference and accurate decision-making is to compute the marginal probabilities or most probable states of task-relevant variables. Probab…
Reviving and Improving Recurrent Back-Propagation
Renjie Liao, Yuwen Xiong, Ethan Fetaya +5
In this paper, we revisit the recurrent back-propagation (RBP) algorithm, discuss the conditions under which it applies as well as how to satisfy them in deep neural networks. We s…
Deformable Convolutional Networks
Jifeng Dai, Haozhi Qi, Yuwen Xiong +4
Convolutional neural networks (CNNs) are inherently limited to model geometric transformations due to the fixed geometric structures in its building modules. In this work, we intro…
Deep Feature Flow for Video Recognition
Xizhou Zhu, Yuwen Xiong, Jifeng Dai +2
Deep convolutional neutral networks have achieved great success on image recognition tasks. Yet, it is non-trivial to transfer the state-of-the-art image recognition networks to vi…