Kai Yao 姚 凯
Kai dot Yao at liverpool dot ac dot uk
I'm a researcher in Ant Group working on privacy-preserving large fondationa models. Meanwhile, I am a PostDoc in University of Zhejiang advised by Prof. Jianke Zhu and CTO Wei Wang. My research background lies in computer vision and transfer learning.
I did my PhD at at University of Liverpool, advised by Prof. Kaizhu Huang and Prof. Jie
Sun. Previously, I completed B.Eng. at Xi'an
Jiaotong-Liverpool University.
English CV  / 
Chinese CV  / 
Google Scholar
 / 
Github
|
|
News
- DEC 2023 - Our papers accepted in AAAI24.
- Aug 2023 - Our papers accepted as Oral Presentation in ACM CIKM2023.
- May 2023 - Our two journal papers accepted in IEEE TETCI and IJB.
- show more
- Nov 2022 - Our conference paper accepted in AAAI'23. We propose a novel augmentation for
medical image domain generalization.
The code released at here.
- Jul 2022 - Our conference paper accepted in ECCV'22. We propose a novel hybrid
vision-transformer-based GAN for image outpainting.
The code released at here.
- Jun 2022 - Our journal paper accepted in IEEE-JBHI (IF: 7.0).
- Dec 2021 - Our team PremiLab wins 5th in the Challenge CrossMoDa
2021 (MICCAI workshop).
- Dec 2021 - Our journal paper accepted in International Journal of Bioprinting (IF:
7.4).
- Nov 2021 - Our journal paper accepted in Cognitive Computation (IF: 4.9).
- Dec 2019 - I started my PhD course at UoL PremiLab Lab with full scholarship.
|
Publication
Sort by publication time. First author papers are highlighted.
|
|
Unraveling Batch Normalization for Realistic Test-Time Adaptation
Zixian Su,
Jingwei Guo,
Kai Yao,
Xi Yang,
Qiufeng Wang,
Kaizhu Huang,
Association for the Advancement of Artificial Intelligence (AAAI), 2024
A novel strategy for training-free test-time adaptation.
|
|
Explore Epistemic Uncertainty in Domain Adaptive Semantic Segmentation
Kai Yao,
Zixian Su,
Xi Yang,
Jie Sun,
Kaizhu Huang,
ACM International Conference on Information and Knowledge Management (CIKM) Oral, 2023
A novel episteme-based framework for domain adaptive semantic segmentation.
|
|
Machine learning and 3D bioprinting
Jie Sun,
Kai Yao,
Jia An,
Linzhi Jing,
Kaizhu Huang,
Dejian Huang
International Journal of Bioprinting (IJB), 2023
A review paper summarize past works and reveal the current challenging towards bioprinting.
|
|
PointNu-Net: Simultaneous Multi-tissue Histology Nuclei Segmentation and
Classification in the Clinical Wild
Kai Yao,
Kaizhu Huang,
Jie Sun,
Amir Hussain,
Curran Jude
IEEE Transactions on Emerging Topics in Computational Intelligence (TETCI), 2023
In this study, we proposed a novel keypoint-aware method to to simultaneously detect,
segment, and classify nuclei from Haematoxylin and Eosin (H&E) stained histopathology
data.
|
|
Mind The Gap: Alleviating Local Imbalance for Unsupervised Cross-Modality Medical Image Segmentation
Zixian Su,
Kai Yao,
Xi Yang,
Qiufeng Wang,
Yuyao Yan,
Kaizhu Huang,
IEEE Journal of Biomedical and Health Informatics (JBHI), 2023
We propose a novel strategy to alleviate the domain gap imbalance considering the characteristics of medical images, namely Global-Local Union Alignment.
|
|
Machine Learning Methods in Skin Disease Recognition: A Systematic Review
Jie Sun,
Kai Yao,
Guangyao Huang,
Chengrui Zhang,
Mark Leach,
Kaizhu Huang,
Xi Yang,
Processes, 2023
This paper overviews the status and progress of ML applications for skin disease recognition.
|
|
Rethinking Data Augmentation for Single-source Domain Generalization in
Medical Image Segmentation
Zixian Su*,
Kai Yao*,
Xi Yang,
Qiufeng Wang,,
Jie Sun,
Kaizhu Huang
(*equal contribution)
Association for the Advancement of Artificial Intelligence (AAAI), 2023
poster
/
arXiv
/
GitHub
We design a novel augmentation for medical image domain generalization and theoretically
prove that our proposed augmentation can lead to an upper bound of the generalization
risk on the unseen target domain.
|
|
Outpainting by Queries
Kai Yao*,
Penglei Gao*,
Xi Yang,
Jie Sun,
Rui Zhang,
Kaizhu Huang
(*equal contribution)
European Conference on Computer Vision (ECCV), 2022
poster
/
arXiv
/
GitHub
we propose a novel hybrid vision-transformer-based encoder-decoder framework, named
Query Outpainting TRansformer (QueryOTR), for extrapolating visual context all-side
around a given image.
|
|
A novel 3D unsupervised domain adaptation framework for cross-modality
medical image segmentation
Kai Yao*,
Zixian Su*,
Kaizhu Huang,
Xi Yang,
Jie Sun,
Amir Hussain,
Frans Coenen
(*equal contribution)
IEEE Journal of Biomedical and Health Informatics (JBHI), 2022
GitHub
We proposed a novel GAN for diverse style transfer, and a 3D Dual Attention Residual
U-Net for robust and reliable cross-modality semantic segmentation.
|
|
Machine learning applications in scaffold based bioprinting
Jie Sun,
Kai Yao,
Kaizhu Huang,
Dejian Huang,
Materials Today: Proceedings, 2022
This paper overviews the status and progress of ML applications from several aspects:
parameter optimization in the fabrication model, in situ monitoring and control,
scaffold performance evaluation, and material design.
|
|
Analyzing cell-scaffold interaction through unsupervised 3d nuclei
segmentation
Kai Yao,
Jie Sun,
Kaizhu Huang,
Lingzhi Jing,
Hang Liu,
Dejian Huang,
Curran Jude
International Journal of Bioprinting, 2021
Taking advantages of AD-GAN, in this paper, we study with cell-scaffold interaction.
|
|
AD-GAN: End-to-end unsupervised nuclei segmentation with aligned
disentangling training
Kai Yao,
Kaizhu Huang,
Jie Sun,
Curran Jude
Preprint, under review., 2021
We developed herein an end-to-end model called Aligned Disentangled Generative
Adversarial Network (AD-GAN) for 3D unsupervised nuclei segmentation of CLSM images.
|
|
Electrohydrodynamic jet-printed ultrathin polycaprolactone scaffolds
mimicking bruch’s membrane for retinal pigment epithelial tissue engineering
Hang Liu, Fan Wu, Renwei Chen, Yanan Chen, Kai Yao, Zengping Liu, Bhav
Harshad Parikh, Linzhi Jing, Tiange Liu, Xinyi Su, Jie Sun, Dejian Huang
International Journal of Bioprinting, 2021
The purpose of this work is to build and evaluate the performance of ultrathin scaffolds
with an electrohydrodynamic jet (EHDJ) printing method for RPE cell culture.
|
|
Scaffold-A549: a benchmark 3D fluorescence image dataset for unsupervised
nuclei segmentation
Kai Yao,
Kaizhu Huang,
Jie Sun,
Lingzhi Jing,
Dejian Huang,
Curran Jude
Cognitive Computation, 2021
GitHub
In this paper, we introduce a new benchmark nuclei segmentation dataset termed as
Scaffold-A549 for 3D cell culture on bio-scaffold.
|
|
Noninvasive In Vivo Imaging and Monitoring of 3D-Printed Polycaprolactone
Scaffolds Labeled with an NIR Region II Fluorescent Dye
Lingzhi Jing,Mingtai Sun, Pingkang Xu, Kai Yao, Jiao Yang, Xiang Wang, Hang
Liu, Minxuan Sun, Yao Sun, Runyan Ni, Jie Sun, Dejian Huang
ACS Applied Bio Materials, 2021
In this paper, I mainly contribute to the visualization.
|
|
Improving deep neural network performance by integrating kernelized Min-Max
objective
Qiufeng Wang,, Kai Yao, Rui Zhang, Amir Hussain, Kaizhu Huang
Neurocomputing, 2020
In this paper, we propose to integrate a kernelized Min-Max objective in the DNN
training in order to explicitly enforce both kernelized within-class compactness and
between-class margin.
|
|
Improving Deep Neural Network Performance with Kernelized Min-Max
Objective
Kai Yao, Kaizhu Huang, Rui Zhang, Amir Hussain
International Conference on Neural Information Processing (ICONIP), 2018
In this paper, we propose to integrate a kernelized Min-Max objective in the DNN
training in order to explicitly enforce both kernelized within-class compactness and
between-class margin.
|
|