CV

Link of Publications


Zhihao Ouyang

Tel: +86-130-4123-1913 | E-mail: oyzh888@foxmail.com| Website:http://www.ouyangzhihao.com

Education Background

Tsinghua & Carnegie Mellon University      Beijing. China& Pittsburgh. USA.               09/2018- Present

  • CMU master of computer science (MSCS) & THU-CMU double degree program                            

Beihang University (BUAA)               Beijing. China                                09/2013- 07/2018

  • Bachelor of Engineering in Software Engineering & Minor in English      Rank 1 out of 141
  • GPA: Major 3.88/4.0 & Minor 3.94/4.0

Publication

  • Zhihao O. Yihang Y, Kun Y, Jian W, Xiaolin H. XiaoJoy: Using Locally Connected CNN to Cooperate with Human Composers (Artwork). Conference on Neural Information Processing System (NeurIPS)Workshop 2018.
  • Zhihao O. Yan F, Zihao H, Tianbo H, Tao D, Shu-Tao X. AttentionDrop for Convolutional Neural Networks. International Conference on Multimedia and Expo (ICME)2019.
  • Zhihao O, Yuyuan Z, Zihao H, Yinghua G, Tao D, Shu-Tao X. Towards Randomness in Learning Rates.International Joint Conferences on Artificial Intelligence (IJCAI)2019 (under review).
  • Lu Y, Zhihao O, Xu S. HTML/CSS/JS Website Design and Development Case. Tsinghua University Press.
  • Lu Y, Xu S, Zhihao O. When Deep Learning Meets Computer Vision. Tsinghua University Press (under review).
  • Lu Y, Zhihao O. Introduction and Application of JavaScript. Tsinghua University Press (under review).

Work and Project Experience

Tsinghua University                              Shenzhen. China                              09/2018– Present

Researcher                     Mentor: Prof. Shu-Tao Xia

  • Randomization research. Adaptive Dropoutfor better regularization than original Dropout. Use random learning rate to bring variance to the backpropagation gradient for better optimization and enhance the model’s robustness.
  • Utilized the LID (Local Intrinsic Dimensionality) to analyze the data and organize a better data distribution for training.

Tsinghua University & Deep Music Company   Beijing. China                    04/2018– 12/2018

Intern Researcher               Mentor: Prof. Xiaolin Hu

  • Used Bi-LSTM, Seq2Seq and other LSTM models for music generation.
  • Designed CNN based on resNet and Locally Connected CNN structure to replace the existing RNN generation model, achieving higher precision and speed in the task of sequence generation.

Face++ Company                   Beijing. China                             04/2018- 2/2019                  

Intern

  • Designed face feature extraction network, using series structure such as Inception Block, Group Conv, IBNNet to improve network robustness and speed.
  • The study of feature regularization, using the ideas of the NormFace series of articles, and improved the optimization objective of the classification from the perspective of the angle.
  • Metric learning research. Improved the traditional triplet-loss on face recognition with n-pair loss, angular loss.
  • Nist’s 2018 Face Recognition Vendor Test (FRVT) achieved the top 5 results (Megvii Team, still in progress).

Goertek Company                  Beijing/Shandong, China                   12/2017– 04/2018

Intern

  • Designed a defect detection system for the iPhone microphone production line involves the use of latest computer vision algorithms such as classification, segmentation, and detection.
  • Based on DenseNet and InceptionResNet, implemented a fast classification model. With the segmentation model based on Mask-RCNN, the accuracy of 99.5% and the speed of 50 milliseconds per component were achieved. Core algorithm for a 0.2 billion $ detection system.

Microsoft Research Asia (MSRA)     Beijing, China                            05/2017– 08/2017

Intern

  • Maintained Microsoft Face API’s customer-related code, developed face recognition related technology.
  • Used LSTM to predict music chords, created interactive UI, and the relevant results were selected as the demoware in the MSRA showroom.
  • AI composer MelodyMaster won Award of Most Creative in Microsoft Hackathon 2017 (2 of 12824 teams).

Personal Projects

SoundMix                         Team Leader                             09/2017– 04/2018

  • Designed smart audio recognition software on iOS by using Fast Fourier Transform Algorithm (FFT) to realize the recognition for the pitch of instruments.
  • Won the venture capital by Beijing Mousse Company.

ChordMixer                       Team Leader                              05/2017– 08/2017

  • Familiar with algorithmic composition. Generated multi-track music with machine learning. Deployed project on both Windows and Android platform.
  • Designed the music chord prediction model base on the process of the HMM chain.
  • Product was exhibited at the China Silk Road Science Festival. Gave speech on International Collegiate Design and Innovation Competition(ICDIC).

Skills

  • Programming Language: Python, C/C++, C#, HTML, JavaScript etc.
  • Frameworks: Tensorflow, Keras, .Net, JQuery, Bootstrap.
  • Additional Skills: Product Presentation, Violin, Piano, Guitar, Composition, Design, Painting.

Competitions & Awards

  • Future Cup Chinese College AI challenge, second place in Beijing                          06/2018
  • Merit undergraduate student in Beijing                                              06/2018
  • Champion, bestTechnology Awards(also the best design and innovation), MSRA Hackathon.      04/2018
  • 1st winner of ShenYuan Medal (10 winners annually) Highest honor for students in BUAA.12/2017
  • Merit Student (top 5%), 3 times, BUAA.                  10/2014-10/2017
  • Award of Most Creative (awarded to 2 of 14000 teams), Microsoft Global Hackathon    07/2017
  • National Scholarship (awarded to top 0.2% Chinese students).                               10/2016
  • Second Place Internationally in Tencent International Cooperation Contest of Innovation and Entrepreneurship, (Awarded to 2 of 4000 teams).    08/2016