Dawei Yang

Dawei Yang

Ph.D. Candidate at the University of Michgan

CV

About Me

I am a 3rd year PhD student, graduate student research assistant (GSRA) at the University of Michigan.

As a member of Michigan Vision and Learning Lab directed by Prof. Jia Deng, I am doing research in computer vision and machine learning. Specifically, my research focuses on improving the performance of vision tasks such as inverse rendering, 3D reconstruction with the aid of computer graphics techniques.

Latest Projects


project name

Decorrelated Batch Normalization

Lei Huang, Dawei Yang, Bo Lang, Jia Deng
IEEE Conference on Computer Vision and Pattern Recognition (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 

project name

Single-Image Depth Perception in the Wild

Weifeng Chen, Zhao Fu, Dawei Yang, Jia Deng
Neural Information Processing Systems (NIPS), 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