Yunhe Gao @ Rutgers

Brief Bio. I am a PhD candidate in the Computer Science Department of Rutgers University, advised by Distinguished Professor Dimitris N. Metaxas.

My current research interests lie primarily in (1) meidcal imaging foundation models (e.g., universal medical image understanding, multimodal models), (2) Knowledge-driven models and explainable AI (e.g., injecting human prior knowledge into models, making the AI decision-making process human-understandable), and (3) Model adaptability (e.g., domain adaptation, generalization, in-context learning).

617 Bowser Rd
Piscataway, NJ 08854
Rutgers University

Email: yunhe [dot] gao [at] rutgers [dot] com
[Curriculum Vitae]

Background

Education

Sept. 2019 - Present

Rutgers, The State University of New Jersey. Piscataway, NJ

Ph.D. in Computer Science

Supervised by Distinguished Prof. Dimitris N. Metaxas

Sept. 2017 - Nov. 2018

The Chinese University of Hong Kong. Central Ave, Hong Kong

M.S. in Electronic Engineering

Supervised by Prof. Hongsheng Li

Sept. 2013 - Jul. 2017

University of Science and Technology of China, Hefei, China

B.Eng. in Automation

Experience

Feb. 2024 - Present

Could + AI, Microsoft. Remote

Part-time Research Scientist Intern.

Medical imaging foundation models

Jun. 2023 - Sep. 2023

Deep Engine Science, AWS. Santa Clara, CA, USA

Applied Scientist Intern. Host: Dr. Boran Han and Dr. Zhiqiang Tang

Large-scale dataset distillation via purified pretraining model

June 2022 - Sep. 2022

Deep Engine Science, AWS. Santa Clara, CA, USA

Applied Scientist Intern. Host: Dr. Xingjian Shi and Dr. Yi Zhu

Data-efficient test-time domain adaptation via visual prompt tuning

Sept. 2019 - Present

Computer Science Department, Rutgers University. Piscataway, NJ, USA

Research Assistant. Supervised by Prof. Dimitris N. Metaxas

Knowledge-driven models for explainable diagnosis
Foundation medical image segmentation models
Improving model robustness against distribution shift
Medical image segmentation via vision transformer
Data-efficient learning via automatic data augmentation for natural and medical images
Shape regularization in medical image segmentation

Selected Publications

Please check Google Scholar for the full list of my publications.)

Aligning Human Knowledge with Visual Concepts Towards Explainable Medical Image Classification

Yunhe Gao, Difei Gu, Mu Zhou, Dimitris Metaxas.

International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), 2024. Early Accept.

[Paper]

Training Like a Medical Resident: Universal Medical Image Segmentation via Context Prior Learning

Yunhe Gao, Zhuowei Li, Di Liu, Mu Zhou, Shaoting Zhang, Dimitris N. Metaxas.

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2024.

LEPARD: Learning Explicit Part Discovery for 3D Articulated Shape Reconstruction

Di Liu, Anastasis Stathopoulos, Qilong Zhangli, Yunhe Gao, Dimitris N. Metaxas.

Advances in Neural Information Processing Systems (NeurIPS), 2023.

[Paper]

Visual prompt tuning for test-time domain adaptation

Yunhe Gao, Xingjian Shi, Yi Zhu, Hao Wang, Zhiqiang Tang, Xiong Zhou, Mu Li, Dimitris N. Metaxas.

Tech Report.

[Paper]

Region proposal rectification towards robust instance segmentation of biological images

Qilong Zhangli, Jingru Yi, Di Liu, Xiaoxiao He, Zhaoyang Xia, Qi Chang, Ligong Han, Yunhe Gao, Song Wen, Haiming Tang, He Wang, Mu Zhou, Dimitris Metaxas.

International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), 2022. Early Accept.

[Paper]

Transfusion: multi-view divergent fusion for medical image segmentation with transformers

Di Liu, Yunhe Gao, Qilong Zhangli, Ligong Han, Xiaoxiao He, Zhaoyang Xia, Song Wen, Qi Chang, Zhennan Yan, Mu Zhou, Dimitris Metaxas.

International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), 2022. Early Accept. Student Travel Award.

[Paper]

A Data-scalable Transformer for Medical Image Segmentation: Architecture, Model Efficiency, and Benchmark

Yunhe Gao, Mu Zhou, Di Liu, Dimitris Metaxas.

Under Review.

UTNet: A Hybrid Transformer Architecture for Medical Image Segmentation

Yunhe Gao, Mu Zhou, Dimitris Metaxas.

International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), 2021.

Enabling data diversity: efficient automatic augmentation via regularized adversarial training

Yunhe Gao, Zhiqiang Tang, Mu Zhou, Dimitris N. Metaxas.

International Conference on Information Processing in Medical Imaging (IPMI), 2021.

[Paper]

Crossnorm and selfnorm for generalization under distribution shifts

Zhiqiang Tang, Yunhe Gao, Yi Zhu, Zhi Zhang, Mu Li, Dimitris N. Metaxas.

IEEE/CVF International Conference on Computer Vision (ICCV), 2021.

FocusNetv2: Imbalanced large and small organ segmentation with adversarial shape constraint for head and neck CT images

Yunhe Gao, Rui Huang, Yiwei Yang, Jie Zhang, Kainan Shao, Changjuan Tao, Yuanyuan Chen, Dimitris N Metaxas, Hongsheng Li, Ming Chen.

Medical Image Analysis, 2021.

OnlineAugment: Online Data Augmentation with Less Domain Knowledge

Zhiqiang Tang, Yunhe Gao, Leonid Karlinsky, Prasanna Sattigeri, Rogerio Feris, Dimitris Metaxas.

European Conference on Computer Vision (ECCV), 2020.

Vertebrae identification and localization utilizing fully convolutional networks and a hidden Markov model

Yizhi Chen, Yunhe Gao, Kang Li, Liang Zhao, Jun Zhao.

IEEE Transactions on Medical Imaging, 2019.

[Paper]

FocusNet: imbalanced large and small organ segmentation with an end-to-end deep neural network for head and neck CT images

Yunhe Gao, Rui Huang, Ming Chen, Zhe Wang, Jincheng Deng, Yuanyuan Chen, Yiwei Yang, Jie Zhang, Chanjuan Tao, Hongsheng Li.

International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), 2019. Early Accept.

[Paper]

Multi-resolution path cnn with deep supervision for intervertebral disc localization and segmentation

Yunhe Gao, Chang Liu, Liang Zhao

International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), 2019. Early Accept.

[Paper]