Avatar

Xia Li

ethanlee AT pku.edu.cn

Ph.D. student

ETH Zurich

Personal Site

Biography

I am a third-year master student at Peking University (PKU). Here I am lucky enough to work with Prof. Zhouchen Lin and Prof. Hong Liu. Before studying in PKU, I obtained my bachelor’s degree from Beijing University of Posts and Telecommunications (BUPT) in 2017.

Interests

  • Computer Vision
  • Semantic Segmentation
  • Low-level Vision

Education

  • M.S. in Computer Engineering, 2017-2020

    Peking University

  • B.S. in Network Engineering, 2013-2017

    Beijing University of Posts and Telecommunications

Internships

 
 
 
 
 

SWE for ML

Google GBoard Team

Apr 2019 – Jul 2019 Beijing
Worked on incremental transliteration model.
 
 
 
 
 

ML Intern

Bytedance AI Lab

Nov 2016 – Mar 2017 Beijing
Worked on human alpha matting.

Publications @ZERO Lab

PointFlow: Flowing Semantics Through Points for Aerial Image Segmentation. CVPR, 2021.

Aerial Image Segmentation is a particular semantic segmentation problem and has several challenging characteristics that general …
Xiangtai Li , Hao He , Xia Li , Duo Li , Guangliang Cheng , Jianping Shi , Lubin Weng , Yunhai Tong , Zhouchen Lin
PDF Code

Is Attention Better Than Matrix Decomposition?. ICLR, 2021.

As an essential ingredient of modern deep learning, attention mechanism, especially self-attention, plays a vital role in the global …
Zhengyang Geng , Meng-Hao Guo , Hongxu Chen , Xia Li , Ke Wei , Zhouchen Lin
PDF

Improving Semantic Segmentation via Decoupled Body and Edge Supervision. ECCV, 2020.

Existing semantic segmentation approaches either aim to improve the object’s inner consistency by modeling the global context, or …
Xiangtai Li , Xia Li , Li Zhang , Guangliang Cheng , Jianping Shi , Zhouchen Lin , Shaohua Tan , Yunhai Tong

Spatial Pyramid Based Graph Reasoning for Semantic Segmentation. CVPR, 2020.

The convolution operation suffers from a limited receptive filed, while global modeling is fundamental to dense prediction tasks, such …
Xia Li , Yibo Yang , Qijie Zhao , Tiancheng Shen , Zhouchen Lin , Hong Liu
PDF

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.
PDF

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.
PDF Code Slides

Expectation Maximization Attention Networks for Semantic Segmentation. ICCV, 2019.

We formulate the attention mechanism into an expectation-maximization manner and iteratively estimate a much more compact set of bases …
PDF Code Project Slides Zhihu Survey Leaderboard

R^2 Net Recurrent and Recursive Network for Sparse View CT Artifacts Removal. MICCAI, 2019.

We propose a novel neural network architecture to reduce streak artifacts generated in sparse-view 2D Cone Beam Computed To-mography …

Recurrent Squeeze-and-Excitation Net for Single Image Deraining. ECCV, 2018.

We propose a novel deep network architecture based on deep convolutional and recurrent neural networksfor single image deraining.
Xia Li , Jianlong Wu , Zhouchen Lin , Hong Liu , Hongbin Zha
PDF Code Dataset Report

Talks

ICCV Oral. 2019.

Oral presentation for EMANet
Nov 1, 2019 1:35 PM — Nov 11, 2019 1:40 PM Seoul, Korea
Slides

COCO2019. 2019.

Panoptic Segmentation Innovative Award
Oct 27, 2019 10:10 AM — 10:20 AM Seoul, Korea
Slides Report

Recent researches on semantic segmentation. 2019.

Shares the recent researches about semantic segmentation
Apr 7, 2019 3:00 PM — 4:00 PM Beijing, China
Xiangtai Li , Xia Li
Slides Report

"I love Fashion". 2019.

The presentation of our team for Google AI ML Camp
Jan 25, 2019 2:00 PM — 2:20 PM Beijing, China
Xia Li , Chaopeng Zhang , Yang Hu
Slides Report

COCO2018. 2018.

Panoptic Segmentation Runner-Up
Sep 9, 2018 11:45 AM — 12:00 PM Munich, Germany
Slides Report

Awards

Innovative Award (PKU_ZERO Team)

COCO Challenge 2019 Nov 2019
We competed on the Panoptic Segmentation track

National Scholarship

Chinese Ministry of Education Oct 2019

Best Projects

Google AI ML Winter Campe Jan 2019

Runner-up (PKU_360 Team)

COCO Challenge 2018 Oct 2018
We competed on the Panoptic Segmentation track

Chinese Reconstruct scholarship

Peking University Oct 2018

First-class scholarship

Beijing University of Posts and Telecommunications Oct 2016

Beijing Marathon in 4.5 hours

Beijing Marathon Sep 2016

Taishan Marathon in 4 hours

Taishan Marathon Oct 2015

First-class scholarship

Beijing University of Posts and Telecommunications Oct 2015

National Scholarship

Chinese Ministry of Education Oct 2014

Beijing Half-marathon in 2 hours

Beijing Marathon Sep 2014