Xiaomeng Li

Ph.D. Candidate

Rm 1024, Ho Sin-Hang Engineering Building
Dept. of Computer Science and Engineering
The Chinese University of Hong Kong
Shatin, N.T., Hong Kong

Email: xmengli999 at gmail dot com


Biography [CV]

I am currently a forth year Ph.D. student in the Department of Computer Science and Engineering, The Chinese University of Hong Kong (CUHK), where I am fortunate to be co-advised by Prof. Pheng-Ann Heng and Prof. Chi-Wing Fu. Before that, I received the B. Eng. degree from the School of Mechano-Electronic Engineering, Xidian University. I worked with Prof. Kai Xie for undergraduate research.

My research has been focused on two broad themes: the interdisciplinary area of developing AI algorithms for real-world medical imaging applications; and the fundamental problems regarding to low-data regime issues, such as few-shot learning, semi-supervised learning and unsupervised learning.

I spent the summer of 2018 at Tencent AI lab, working with Jia Xu on developing models for few-shot classification.

Honors & Awards

Champion, Liver Tumor Segmentation Challenge Leaderboard , 2017 (util. Oct. 2018, team name:xjqi, code is public online )
Champion, Automatic IVD Localization and Segmentation from 3D Multi-modality MR Images, 2016
National Scholarship in China (0.6%), 2014
First-class student Scholarship (5.0%), 2012, 2013
Honorable Mention, Interdisciplinary Contest in Modeling (ICM), Consortium for Mathematics and Its Application, 2013
National 2nd Prize, Mathematical Contest in Modeling(MCM) (3.10%), 2012.

Selected Publications [Google Scholar]

                     
Xiaomeng Li, Lequan Yu, Chi-Wing Fu, Pheng-Ann Heng. "Deeply supervised rotation equivariant network for lesion segmentation in dermoscopy images" International Skin Imaging Collaboration (ISIC) Skin Image Analysis Workshop of MICCAI 2018. (Oral)

[paper]

Xiaomeng Li, Lequan Yu, Hao Chen, Chi-Wing Fu, Pheng-Ann Heng. "Semi-supervised Skin Lesion Segmentation via Transformation Consistent Self-ensembling Model" The British Machine Vision Conference (BMVC), 2018.

[paper]

Xiaomeng Li, Hao Chen, Xiaojuan Qi, Qi Dou, Chi-Wing Fu, Pheng-Ann Heng. "H-DenseUNet: Hybrid densely connected UNet for liver and liver tumor segmentation from CT volumes." IEEE Transactions on Medical Imaging (IEEE TMI), 2018.

[paper] [code]

Xiaomeng Li, Qi Dou, Hao Chen, Chi-Wing Fu, Xiaojuan Qi, Guoyan Zheng and Pheng-Ann Heng, et al. "3D multi-scale FCN with random modality voxel dropout learning for Intervertebral Disc Localization and Segmentation from Multi-modality MR Images " Medical image analysis (MedIA), 2018.

[paper]

Xiaomeng Li, Qi Dou, Hao Chen, Chi-Wing Fu, Pheng-Ann Heng. "Multi-scale and modality dropout learning for intervertebral disc localization and segmentation" MICCAI Workshop on Computational Methods and Clinical Applications for Spine Imaging, 2016.

[paper]

Lei Zhu, Weiming Wang, Xiaomeng Li, Qiong Wang, Jing Qin, Chi-Wing Fu and Pheng-Ann Heng, et al. "Feature-preserving ultrasound speckle reduction via L0 minimization" Neurocomputing (Neurocomputing), 2018.

[paper]

Lei Zhu, Weiming Wang, Xiaomeng Li, Qiong Wang, Jing Qin, Kin-Hong Wong, Pheng-Ann Heng. "Ultrasound Speckle Reduction via Minimization" Asian Conference on Computer Vision (ACCV), 2016.

[paper]

Experience

Teaching

2015-2016FallCSCI1540 Fundamental computing with C++
2015-2016SpringENGG1100 Introduction to Engineering Design
2016-2017FallCSCI2100 Data structure
2016-2017SpringCSCI3310 Mobile Computing and Applications Development
2017-2018FallCSCI3310 Mobile Computing and Applications Development


© Xiaomeng Li | Last updated: 15 Dec. 2018