Shihao Zhang | School of Computing, National University of Singapore

About Me

I am a final-year Ph.D. student in the CVML Group at the National University of Singapore (NUS), supervised by Prof. Angela Yao. My doctoral research focuses on regression representation learning, using information theory and topology as tools with a theoretical emphasis. In contrast, my master’s research was more application-oriented, concentrating on medical image segmentation. I previously earned my master’s and bachelor’s degrees from the South China University of Technology (SCUT), majoring in Software Engineering and Mathematics, respectively.

Regression representation learning[1, 2, 3]: Exploring the differences between classification (with categorical targets) and regression representations (with continuous targets), providing a deeper understanding of both. The insights gained benefit a wide range of regression tasks, e.g., depth estimation, super-resolution, pose estimation, and age estimation.
Medical image segmentation [4, 5, 6]: Exploring the structural and textural information and focusing on better handling blurred boundaries.
Additional Research Experience[7]: During the early stages of my master’s studies, I gained research experience in Click-Through Rate prediction and super-resolution. I also have experience in clinical research from my work at the Singapore National Eye Centre. Recently, I

Selected Publications

[1] S. Zhang, Y. Yan, and A. Yao. Improving Deep Regression with Tightness. ICLR 2025. [Paper], [Code]

[2] S. Zhang, K. Kawaguchi, and A. Yao. Deep Regression Representation with Topology. ICML 2024. [Paper], [Code], [Project]

[3] S. Zhang, L. Yang, M. Bi Mi, X. Zheng, and A. Yao. Improving Deep Regression with Ordinal Entropy. ICLR. 2023. [Paper], [Code], [Project]

[4] S. Zhang, H. Fu, Y. Xu, Y. Liu, and M. Tan. Retinal Image Segmentation with Structure-Texture Demixing Network. MICCAI. 2020. [Paper]

[5] S. Zhang, H. Fu, Y. Yan, Y. Zhang, Q. Wu, M. Yang, M. Tan, and Y. Xu. Attention Guided Network for Retinal Image Segmentation. MICCAI. 2019. [Paper], [Code]

[6] S. Zhang, Y. Yan, et al. Guided M-Net for High-resolution Biomedical Image Segmentation with Weak Boundaries and Noise. MICCAI workshop on OMIA. 2019 (best paper). [Paper]

[7] WY Ng, S. Zhang, et al. Updates in Deep Learning Research in Ophthalmology. Clinical Science. 2021. [Paper]

Teaching

Machine Learning, SCUT, Teaching Assistant, 2018
Deep Learning, SCUT, Teaching Assistant, 2018
GEI1000 & GET1031 Computational Thinking, NUS, Teaching Assistant, 2022
Special mini computational thinking course over 2 weeks for 60 students from the University of Electronic Science and Technology of China, Teaching Assistant for Prof. Leong How Wai, 2022