Jiahui Yu

Ph.D. student, UIUC

2029 Beckman Institute,
405 North Mathews Avenue,
Urbana, Illinois 61801.


I am a third year Ph.D. student advised by Professor Thomas Huang. My interest is in machine perception, generative models and high performance computing. I received B.E. at School of the Gifted Young in Computer Science, University of Science and Technology of China in 2016.


Publications

(Google Scholar)

Slimmable Neural Networks
Jiahui Yu, Linjie Yang, Ning Xu, Jianchao Yang, Thomas Huang.
ICLR 2019 / Code / OpenReview
Top-10 rated papers on OpenReview, ICLR 2019.

Free-Form Image Inpainting with Gated Convolution
Jiahui Yu, Zhe Lin, Jimei Yang, Xiaohui Shen, Xin Lu, Thomas Huang.
Preprint / Code / Project

Wide Activation for Efficient and Accurate Image Super-Resolution
Jiahui Yu, Yuchen Fan, Jianchao Yang, Ning Xu, Zhaowen Wang, Xinchao Wang, Thomas Huang.
Preprint (challenge report) / Code
Won 1st in NTIRE Challenge on Single Image Super-Resolution, CVPR 2018.

Generative Image Inpainting with Contextual Attention
Jiahui Yu, Zhe Lin, Jimei Yang, Xiaohui Shen, Xin Lu, Thomas Huang.
CVPR 2018 / Code / Project / Demo (10,000+ trials in 72 hours after release)

UnitBox: An Advanced Object Detection Network
Jiahui Yu, Yuning Jiang, Zhangyang Wang, Zhimin Cao, Thomas Huang.
ACMMM 2016