C
Chenxin Li
Researcher at Xiamen University
Publications - 10
Citations - 62
Chenxin Li is an academic researcher from Xiamen University. The author has contributed to research in topics: Segmentation & Supervised learning. The author has an hindex of 1, co-authored 10 publications receiving 3 citations.
Papers
More filters
Posted Content
Few-shot Medical Image Segmentation using a Global Correlation Network with Discriminative Embedding
TL;DR: This study constructed a few-shot image segmentation mechanism using a deep convolutional network trained episodically and developed an efficient global correlation module to model the correlation between a support and query image and incorporate it into the deep network.
Journal ArticleDOI
Few-shot Medical Image Segmentation using a Global Correlation Network with Discriminative Embedding.
TL;DR: In this article, a few-shot image segmentation mechanism using a deep convolutional network trained episodically is proposed. But, the method requires massive annotations in training to avoid overfitting and is difficult to acquire where biomedical expert knowledge is required.
Proceedings ArticleDOI
Unsupervised Large-Scale Social Network Alignment via Cross Network Embedding
Zhehan Liang,Yu Rong,Chenxin Li,Yunlong Zhang,Yue Huang,Tingyang Xu,Xinghao Ding,Junzhou Huang +7 more
TL;DR: Wang et al. as discussed by the authors proposed an unsupervised alignment framework named Large-Scale Network Alignment (LSNA) to integrate the network information and reduce the requirement on user profile.
Posted Content
Domain Generalization on Medical Imaging Classification using Episodic Training with Task Augmentation.
TL;DR: In this paper, a novel domain generalization (DG) scheme of episodic training with task augmentation on medical imaging classification is proposed, which is based on model-agnostic meta-learning (MAML).
Book ChapterDOI
Generator Versus Segmentor: Pseudo-healthy Synthesis
Yunlong Zhang,Chenxin Li,Xin Lin,Liyan Sun,Yihong Zhuang,Yue Huang,Xinghao Ding,Xiaoqing Liu,Yizhou Yu +8 more
TL;DR: Zhang et al. as mentioned in this paper proposed a divide-and-conquer strategy to solve the problem of pseudo-healthy synthesis, which is defined as synthesizing a subject-specific pathology-free image from a pathological one.