Welcome to Jianyu Wang's Homepage!

About
I am Jianyu Wang, currently a Research Scientist at Institute of Deep Learning (IDL) in Baidu Research USA from April 2017.

I obtained the Ph.D. degree from the Statistics Department of UCLA in March 2017. During my Ph.D., I was very fortunate to work with Prof. Alan Yuille in the field of computer vision and deep learning. I obtained the master degree from the Electrical Engineering Department of UCLA in June 2013, where I majored in optimization and signal processing. Before that, I did my undergraduate in the Electronic Engineering Department, Tsinghua University from 2007 to 2011. I did summer internship twice at Google, Mountain View, in 2015 and 2016. 

Email: wjyouch[AT]gmail[DOT]com 




Research Interests

My research interests generally lie in computer vision and deep learning. Specifically, I take interests in:
1). Part and Compositions, Object Recognitions
2). Deep Learning Visualization and Understanding
3). Adversarial Attack and Defense in Machine Learning Systems
4). Incremental / Continue learning



Publications

Preprints
Bilateral Adversarial Training: Towards Fast Training of More Robust Models Against Adversarial Attacks, arXiv, 2018
Jianyu Wang

Zero-Shot Transfer VQA Dataset, arXiv, 2018
Yuanpeng Li, Yi Yang, Jianyu Wang, Wei Xu

Adversarial Attacks and Defences Competition, arXiv, 2018
Alexey Kurakin, Ian Goodfellow, Samy Bengio, Yinpeng Dong, Fangzhou Liao, Ming Liang, Tianyu Pang, Jun Zhu, Xiaolin Hu, Cihang Xie, Jianyu Wang, Zhishuai Zhang, Zhou Ren, Alan Yuille, Sangxia Huang, Yao Zhao, Yuzhe Zhao, Zhonglin Han, Junjiajia Long, Yerkebulan Berdibekov, Takuya Akiba, Seiya Tokui, Motoki Abe

Improving Transferability of Adversarial Examples with Input Diversity, arXiv, 2018.
Cihang Xie, Zhishuai Zhang, Jianyu Wang, Yuyin Zhou, Zhou Ren, Alan Yuille

Unsupervised Learning of Object Semantic Parts from Internal States of CNNs by Population Encoding, arXiv, 2016. 
Jianyu Wang, Zhishuai Zhang, Cihang Xie, Vittal Premachandran, Alan Yuille


Conferences

DeepVoting: An Explainable Framework for Semantic Part Detection under Partial Occlusion, CVPR, 2018.

Zhishual Zhang*, Cihang Xie*, Jianyu Wang*, Lingxi Xie, Alan Yuille (*equal contribution)

Mitigating adversarial effects through randomization, ICLR, 2018.

Cihang Xie, Jianyu WangZhishual Zhang, Zhou Ren, Alan Yuille

[paper] [code]


Adversarial Examples for Semantic Segmentation and Object Detection, ICCV, 2017.
Cihang Xie*, Jianyu Wang*, Zhishuai Zhang*, Yuyin Zhou, Lingxi Xie, Alan Yuille (*equal contribution)

Detecting Semantic Parts on Partially Occluded Rigid Objects, BMVC, 2017.
Jianyu Wang*, Cihang Xie*, Zhishuai Zhang*, Lingxi Xie, Jun Zhu, Alan Yuille (*equal contribution)
[paper] [VehicleSemanticPart dataset for semantic part detection], [VehicleOcclusion dataset for part detection under occlusion]

Semantic Part Segmentation using Compositional Model combining Shape and Appearance, CVPR, 2015.
Jianyu Wang, Alan Yuille
[paper], [HorseCow dataset for shape analysis]

Journals
Visual Concepts and Compositional Voting, Annals of Mathematical Sciences and Applications, 2018.
Jianyu Wang, Zhishual Zhang, Cihang Xie, Yuyin Zhou, Vittal Premachandran, Jun Zhu, Lingxi Xie, Alan Yuille
[paperThis journal paper combines two conference papers into a complete framework.



Industrial Experiences
Software Engineer Research Intern, Google, Mountain View, CA.        06/2016 - 12/2016
  • Fashion style using TensorFlow, Mobile Vision, Google Research.
Software Engineer Intern, Google, Mountain View, CA.                        06/2015 - 09/2015
  • Keyword expansion using DistBelief, Predictive Targeting, Content Ads.