• Zhihao Ouyang

    +1 (571) 523-5851


    Carnegie Mellon University



    Ø  Master of Computer Science (MSCS)

    Tsinghua University



    Ø  Master of Computer Science , THU-CMU double degree program

    Beihang University (BUAA)



    Ø  Bachelor of Engineering in Software Engineering & Minor in English; Rank 1 out of 141

    Ø  GPA: Major 3.88/4.0 & Minor 3.94/4.0; Graduate with Shenyuan Honor (Highest honor for students)


    [1].  Zhihao O, Yuyuan Z, Zihao H, Yinghua G, Tao D, Shu-Tao X. Towards Randomness in Learning Rates. AAAI Conference on Artificial Intelligence (AAAI) 2020 (under review).

    [2].  Zhihao O. Haoyu L, Yuyuan Z, Zihao H, Hang S, Jun Z, Shu-Tao X. Channel Specified Convolutional Neural Network. International Conference on Learning Representations (ICLR) 2020 (under review).

    [3].  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.

    [4].  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.

    [5].  Lu Y, Zhihao O, Xu S. Website Design and Development Case. Tsinghua University Press 2018.


    Interpretability and distangle of Convolutional Neural Network

    03/2019– Present

    Research Assistant, Advisor: Prof.Jun Zhu

    Department of Computer Science & technology, Tinghua University

    Ø  Used channel-class gates and loss function to interprate the behavior of CNN kernels.

    Ø  Disentangle the CNN kernals using limit function and staged training methods.

    Regulization and Robustness of Deep Learning Model

    09/2018– Present

    Department of Computer Science & Technology, Tsinghua University

    Research Assistant, Advisor: Prof.Shutao Xia

    Ø  Proposed Adaptive Dropout for better regularization than original Dropout for CNN models.

    Ø  Utilized random learning rate to bring variance to the backpropagation gradient for better optimization and enhance the model’s robustness.

    Music Generation Research and Engineering

    04/2018– 12/2018

    Tsinghua University & Deep Music company

    Research Assistant, Advisor: Prof. Xiaolin Hu

    Ø  Used Bi-LSTM, Seq2Seq and other LSTM models for music generation.

    Ø  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.

    Ø  Models were successfully used in Deep Music company and appeared on TV show “The Voice of China”.

    Face Recognition Research

    04/2018- 2/2019

    Megvii(Face++) Company

    Research Intern, Mentor: Dr.Dong Li

    Ø  Designed face feature extraction network, using series structure such as Inception Block, Group Conv, IBNNet to improve network robustness and speed.

    Ø  Implemented face feature regularization methods from NormFace series of articles, and improved the optimization objective of the classification from the perspective of the angle.

    Microsoft Congnitive Service Face API

    05/2017– 08/2017

    Microsoft Research Asia (MSRA)

    Intern, Mentor: Gang Chen (Principle Manager)

    Ø  Maintained Microsoft Face API’s customer-related code, developed face recognition related technology.

    Ø  AI composer MelodyMaster were selected as the demoware in the MSRA showroom and won Award of Most Creative in Microsoft Hackathon (2/12824 ).

    Projects and Entrepreneurship

    Industrial defect detection system

    1/2019– Present

    Wise Sense Company

    Co-Founder & CTO

    Ø  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.

    Ø  Based on DenseNet and InceptionResNet, implemented a fast classification model. The accuracy of 99.5% and the speed of 50 milliseconds per component were achieved. Core algorithm for a 0.2 billion $ detection system.

    Music Auto-Accompaniment Software “SoundMix” and “ChordMixer”


    SoundMix and ChordMixer Project

    Team Leader

    Ø  Developed a smart audio recognition software on iOS by using Fast Fourier Transform Algorithm (FFT) to realize the recognition for the pitch of instruments.

    Ø  Finished road show in Tencent headquarter; won the second place (2/4000) and the Outstanding Creative Award (5/4000) in Tencent Innovation and Entrepreneurship Competition,.

    Ø  Purchased by the Beijing Mousse Company.


    Ø  Programming Language: Python, C/C++, C#, HTML, JavaScript, Swift etc.

    Ø  Frameworks: Tensorflow, Keras, Pytorch, Flask, JQuery, Bootstrap

    Ø  Additional Skills: Product Presentation, Violin, Piano, Guitar, Composition, Design, Painting.