Avatar

Hongyang Li

lhy_ustb AT pku.edu.cn

Engineer

Tusimple Inc.

Personal Site

Biography

I am a third-year CS master student of School of Electronics Engineering and Computer Science, Peking University (PKU). It’s my great honor to be here to learn from Prof. Zhouchen Lin and a lot of excellent lab-mates. Before this, I obtained my bachelor’s degree from University of Science & Technology of Beijing(USTB) and double degree in economics from National School of Development, Peking University (PKU) in 2017.

Interests

  • Computer Vision
  • Object Detection
  • Panoptic Segmentation

Education

  • MSc in Computer Science, 2017-2020

    Peking University

  • BSc in Internet of Things, 2013-2017

    University of Science & Technology of Beijing

  • BSc in Economics (Dual Degree), 2014-2017

    Peking University

Curriculum Vitae

 
 
 
 
 

Intern

Vision Technology Department, Baidu

Jun 2019 – Sep 2019 Beijing

Research on:

  • Object Detection
 
 
 
 
 

Intern

LenzTech

Sep 2018 – Jun 2019 Beijing

Research on:

  • Object Detection

Publications @ZERO Lab

Towards Improving the Consistency, Efficiency, and Flexibility of Differentiable Neural Architecture Search. CVPR, 2021.

Most differentiable neural architecture search methods construct a super-net for search and derive a target-net as its sub-graph for …

ISTA-NAS: Efficient and Consistent Neural Architecture Search by Sparse Coding. NeurIPS, 2020.

Neural architecture search (NAS) aims to produce the optimal sparse solution from a high-dimensional space spanned by all candidate …

Dynamical System Inspired Adaptive Time Stepping Controller for Residual Network Families. AAAI, 2020.

Inspired from the dynamical systems, this study aims to unravel and improve ResNets.

SOGNet: Scene Overlap Graph Network for Panoptic Segmentation. AAAI, 2020.

Our study aims to explicitly predict overlap relations and resolve overlaps in a differentiable way for the panoptic output.

Awards

Innovative Award (PKU_ZERO Team)

We competed on the Panoptic Segmentation track

Runner-up (PKU_360 Team)

We competed on the Panoptic Segmentation track

ACM International Collegiate Programming Contest EC-Final Bronze Medal

Special People’s scholarship