Zixun Zhang
PhD candidate
Liaoning, China
zhangchlr1995 [at] gmail [dot] com
Research interest
Model compression: neural network pruning, NAS, knowledge distillation
Others: evolutionary algorithm, hyper-parameter optimization, adversarial attack, etc.
Languages
Chinese, mother tongue
English, second language
Japanese, JLPT N2
Last update: 2023.09.06
My name is Zixun Zhang. I am now a PhD candidate advised by Dr. Zhen Li with DeepBitLab, FNii at The Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen).
I got my Academic master's degree and Bachelor's degree at Dalian University of Technology (DLUT) advised by Prof. Na Lei and Prof. Lin Lin. During my master's study, I was a visiting student and research assistant at Shenzhen Research Institute of Big Data (SRIBD), CUHK-Shenzhen mentored by Dr. Zhen Li.
My research interest falls in Efficient Deep Learning, and its application on various CV domains especially on medical image analysis. Specifically,
- Optimization Efficiency: aim to train a model better to achieve higher quality metrics (accuracy, F1 score, etc.) and also aim to accelerate the training efficiency.
- Data Efficiency: minimize the dependence on labeled data and enhance the learning efficiency and quality.
- Others: model compression or neural architecture search for compact architecture.
Latest News
- New! 2023.11 - One paper is accepted by Journal of Biomedical and Health Informatics.
- New! 2023.11 - I'm visiting A*STAR as visiting PhD.
- 2023.10 - One paper is accepted by BIBM 2023 as oral presented short paper.
- 2023.06 - One paper is accepted by Computerized Medical Imaging and Graphics.
- 2023.05 - One paper is early accepted by MICCAI 2023.
- 2023.02 - One paper is accepted by TNNLS.
- 2022.09 - One paper is accepted by ACCV 2022.
- 2022.06 - One paper is accepted by ICDCS 2022, EAI Workshop.
- 2020.01 - One paper is accepted by ECAI 2020.
Experience & Education
| PhD candidate at Computer and Information Engineering, CUHK-Shenzhen | Sept 2021 - Present |
| Visiting student and Research assistant, SRIBD, CUHK-Shenzhen | Jun 2019 - Aug 2020 |
| M.Eng. student at Software Engineering, DLUT | Sept 2017 - Jun 2020 |
| B.Eng. student at Software Engineering (Intensive Japanese), DLUT | Sept 2013 - Jun 2017 |
Publications
(* authors contributed equally to this work)-
MetaSelection: Metaheuristic Sub-Structure Selection for Neural Network Pruning Using Evolutionary Algorithm
ECAI 2020 (Oral Presentation!) [PDF] [2020.01]
Zixun Zhang, Zhen Li, Lin Lin, Na Lei, Guanbin Li, Shuguang Cui -
Temperature Annealing Knowledge Distillation from Averaged Teacher
ICDCS 2022 EAI Workshop [PDF] [2022.06]
Xiaozhe Gu, Zixun Zhang, Tao Luo -
APAUNet: Axis Projection Attention UNet for Small Target in 3D Medical Segmentation
ACCV 2022 [PDF] [2022.09]
Yuncheng Jiang*, Zixun Zhang*, Shixi Qin, Yao Guo, Zhen Li, Shuguang Cui -
Hierarchical Weight Averaging for Deep Neural Networks
IEEE Transactions on Neural Networks and Learning Systems [PDF] [2023.02]
Xiaozhe Gu*, Zixun Zhang*, Yuncheng Jiang, Tao Luo, Ruimao Zhang, Shuguang Cui, Zhen Li -
YONA: You Only Need One Adjacent Reference-frame for Accurate and Fast Video Polyp Detection
MICCAI 2023 (Early Accept) [PDF] [2023.05]
Yuncheng Jiang*, Zixun Zhang*, Ruimao Zhang, Guanbin Li, Shuguang Cui, Zhen Li -
NG-NAS: Node growth neural architecture search for 3D medical image segmentation
Computerized Medical Imaging and Graphics [2023.06]
Shixi Qin, Zixun Zhang, Yuncheng Jiang, Shuguang Cui, Shenghui Cheng, Zhen Li -
ScribblePolyp: Scribble-Supervised Polyp Segmentation through Dual Consistency Alignment
BIBM 2023 (Short paper) [PDF] [2023.10]
Zixun Zhang*, Yuncheng Jiang*, Jun Wei, Hanna Cui, Zhen Li -
ECC-PolypDet: Enhanced CenterNet with Contrastive Learning for Automatic Polyp Detection
Journal of Biomedical and Health Informatics [PDF] [2023.11]
Yuncheng Jiang*, Zixun Zhang*, Yiwen Hu*, Guanbin Li, Xiang Wan, Song Wu, Shuguang Cui, Silin Huang, Zhen Li
Services
- Reviewer: ICONIP 2023, ACM MM 2023, ACCV 2022, ISGIE 2022.
- Subreviewer: ECIR 2021, SIGIR 2022.