Dawei Yang

Dawei Yang

Ph.D. Candidate at the University of Michgan

CV

About Me

I am a PhD Candidate at the University of Michigan, advised by Prof. Jia Deng and co-advised by Prof. David Fouhey. As a member of Princeton Vision and Learning Lab, I am doing research in computer vision and machine learning. My research focuses on exploiting compute graphics techniques for improving inverse rendering tasks such as 3D reconstruction, and adversarial attacks in 3D domains.

Latest News

(June 11, 2019) Serving as a Program Committee member of Security and Privacy of Machine Learning workshop at ICML 2019.

(May 24, 2019) Serving as a reviewer for NeurIPS 2019.

(Mar 29, 2019) Serving as a reviewer for ICCV 2019.

(Nov 16, 2018) Serving as a reviewer for CVPR 2019.

Latest Projects


project name

Adversarial Objects Against LiDAR-Based Autonomous Driving Systems

Yulong Cao*, Chaowei Xiao*, Dawei Yang*, Jing Fang, Ruigang Yang, Mingyan Liu, Bo Li

In this paper, we reveal the potential vulnerabilities of LiDAR-based autonomous driving detection systems. We test the generated adversarial objects on the Baidu Apollo autonomous driving platform and show that such physical systems are vulnerable to the proposed attacks. We also 3D-print our adversarial objects and perform physical experiments to illustrate that such vulnerability exists in the real world.

paper  website

project name

MeshAdv: Adversarial Meshes for Visual Recognition

Chaowei Xiao*, Dawei Yang*, Bo Li, Jia Deng, Mingyan Liu
CVPR 2019 (oral)

In this paper we consider adversarial behaviors in practical scenarios by manipulating the shape and texture of a given 3D mesh representation of an object. By generating 3D adversarial perturbation on shape or texture for a 3D mesh, the corresponding projected 2D instance can fool classifiers and object detectors.

paper  oral  poster  bib 

project name

Shape from Shading through Shape Evolution

Dawei Yang, Jia Deng
CVPR 2018 (spotlight)

In this paper, we address the shape-from-shading problem by training deep networks with synthetic images. Our approach consists of two synergistic processes: the evolution of complex shapes from simple primitives, and the training of a deep network for shape-from-shading.

paper  spotlight  poster  bib 

project name

Decorrelated Batch Normalization

Lei Huang, Dawei Yang, Bo Lang, Jia Deng
CVPR 2018

In this work, we propose Decorrelated Batch Normalization (DBN), which not just centers and scales activations but whitens them. DBN retains the desirable qualities of Batch Normalization (BN) and further improves BN's optimization efficiency and generalization ability.

paper  code  bib 

project name

Single-Image Depth Perception in the Wild

Weifeng Chen, Zhao Fu, Dawei Yang, Jia Deng
NeurIPS 2016

This paper studies single-image depth perception in the wild, i.e., recovering depth from a single image taken in unconstrained settings.

paper  dataset  code  supp  bib