Yan Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Yan Wang has a total of 31 co-authors. Here are the top co-authors by number of shared publications:
- Kilian Q. Weinberger
Cornell University Cornell University
2 shared publications - Bharath Hariharan
Cornell University
1 shared publication - Bin Yang
Department of Computer Science University of Toronto
1 shared publication - Boris Ivanovic
NVIDIA Research, Santa Clara, CA, USA
1 shared publication Brian H. Wang
1 shared publication- Brian H. Wang
Mechanical and Aerospace Engineering, Cornell University, Ithaca, NY United States of America 14850
1 shared publication
Latest Publications
- 15 September 2026
- Published by Springer Nature
- p. 547-565
A Physics-Grounded Benchmark for Multi-agent Dynamics in World Models
- 15 September 2026
- Published by Springer Nature
- p. 547-565
A Physics-Grounded Benchmark for Multi-agent Dynamics in World Models
- Open Access
PLUMENet: Efficient 3D Object Detection from Stereo Images
3D object detection is a key component of many robotic applications such as self-driving vehicles. While many approaches rely on expensive 3D sensors such as LiDAR to produce accurate 3D estimates, methods that exploit stereo cameras have recently shown promising results at a lower cost. Existing approaches tackle this problem in two steps: first depth estimation from stereo images is performed to produce a pseudo LiDAR point cloud, which is then used as input to a 3D object detector. However, this approach is suboptimal due to the representation mismatch, as the two tasks are optimized in two different metric spaces. In this paper we propose a model that unifies these two tasks and performs them in the same metric space. Specifically, we directly construct a pseudo LiDAR feature volume (PLUME) in 3D space, which is then used to solve both depth estimation and object detection tasks. Our approach achieves state-of-the-art performance with much faster inference times when compared to existing methods on the challenging KITTI benchmark.
Open AccessPLUMENet: Efficient 3D Object Detection from Stereo Images
3D object detection is a key component of many robotic applications such as self-driving vehicles. While many approaches rely on expensive 3D sensors such as LiDAR to produce accurate 3D estimates, methods that exploit stereo cameras have recently shown promising results at a lower cost. Existing approaches tackle this problem in two steps: first depth estimation from stereo images is performed to produce a pseudo LiDAR point cloud, which is then used as input to a 3D object detector. However, this approach is suboptimal due to the representation mismatch, as the two tasks are optimized in two different metric spaces. In this paper we propose a model that unifies these two tasks and performs them in the same metric space. Specifically, we directly construct a pseudo LiDAR feature volume (PLUME) in 3D space, which is then used to solve both depth estimation and object detection tasks. Our approach achieves state-of-the-art performance with much faster inference times when compared to existing methods on the challenging KITTI benchmark.
- Open Access
SimpleShot: Revisiting Nearest-Neighbor Classification for Few-Shot Learning
Few-shot learners aim to recognize new object classes based on a small number of labeled training examples. To prevent overfitting, state-of-the-art few-shot learners use meta-learning on convolutional-network features and perform classification using a nearest-neighbor classifier. This paper studies the accuracy of nearest-neighbor baselines without meta-learning. Surprisingly, we find simple feature transformations suffice to obtain competitive few-shot learning accuracies. For example, we find that a nearest-neighbor classifier used in combination with mean-subtraction and L2-normalization outperforms prior results in three out of five settings on the miniImageNet dataset.
Open AccessSimpleShot: Revisiting Nearest-Neighbor Classification for Few-Shot Learning
Few-shot learners aim to recognize new object classes based on a small number of labeled training examples. To prevent overfitting, state-of-the-art few-shot learners use meta-learning on convolutional-network features and perform classification using a nearest-neighbor classifier. This paper studies the accuracy of nearest-neighbor baselines without meta-learning. Surprisingly, we find simple feature transformations suffice to obtain competitive few-shot learning accuracies. For example, we find that a nearest-neighbor classifier used in combination with mean-subtraction and L2-normalization outperforms prior results in three out of five settings on the miniImageNet dataset.
- 12 June 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 4 (3) , 2902-2909
LDLS: 3-D Object Segmentation Through Label Diffusion From 2-D Images
Object segmentation in 3D point clouds is a critical task for robots capable of 3D perception. Despite the impressive performance of deep learning-based approaches on object segmentation in 2D images, deep learning has not been applied nearly as successfully for 3D point cloud segmentation. Deep networks generally require large amounts of labeled training data, which are readily available for 2D images but are difficult to produce for 3D point clouds. In this paper, we present Label Diffusion Lidar Segmentation (LDLS), a novel approach for 3D point cloud segmentation which leverages 2D segmentation of an RGB image from an aligned camera to avoid the need for training on annotated 3D data. We obtain 2D segmentation predictions by applying Mask-RCNN to the RGB image, and then link this image to a 3D lidar point cloud by building a graph of connections among 3D points and 2D pixels. This graph then directs a semi-supervised label diffusion process, where the 2D pixels act as source nodes that diffuse object label information through the 3D point cloud, resulting in a complete 3D point cloud segmentation. We conduct empirical studies on the KITTI benchmark data set and on a mobile robot, demonstrating wide applicability and superior performance of LDLS compared to the previous state-of-the-art in 3D point cloud segmentation, without any need for either 3D training data or fine-tuning of the 2D image segmentation model.
- 12 June 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 4 (3) , 2902-2909
LDLS: 3-D Object Segmentation Through Label Diffusion From 2-D Images
Object segmentation in 3D point clouds is a critical task for robots capable of 3D perception. Despite the impressive performance of deep learning-based approaches on object segmentation in 2D images, deep learning has not been applied nearly as successfully for 3D point cloud segmentation. Deep networks generally require large amounts of labeled training data, which are readily available for 2D images but are difficult to produce for 3D point clouds. In this paper, we present Label Diffusion Lidar Segmentation (LDLS), a novel approach for 3D point cloud segmentation which leverages 2D segmentation of an RGB image from an aligned camera to avoid the need for training on annotated 3D data. We obtain 2D segmentation predictions by applying Mask-RCNN to the RGB image, and then link this image to a 3D lidar point cloud by building a graph of connections among 3D points and 2D pixels. This graph then directs a semi-supervised label diffusion process, where the 2D pixels act as source nodes that diffuse object label information through the 3D point cloud, resulting in a complete 3D point cloud segmentation. We conduct empirical studies on the KITTI benchmark data set and on a mobile robot, demonstrating wide applicability and superior performance of LDLS compared to the previous state-of-the-art in 3D point cloud segmentation, without any need for either 3D training data or fine-tuning of the 2D image segmentation model.
- 1 May 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 5893-5900
Anytime Stereo Image Depth Estimation on Mobile Devices
- 1 May 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 5893-5900
Anytime Stereo Image Depth Estimation on Mobile Devices