128 citations
- Fudan UniversityCN8 papers
- Shanghai Center for Brain Science and Brain-Inspired TechnologyCN8 papers
- Chinese Academy of SciencesCN2 papers
- Macau University of Science and TechnologyMO2 papers
- Beijing Academy of Artificial IntelligenceCN1 paper
- Chengdu UniversityCN1 paper
- Henan Academy of SciencesCN1 paper
- Henan Provincial People's HospitalCN1 paper
- Huashan HospitalCN1 paper
- Institute of AutomationCN1 paper
- Institute of Science and Technology1 paper
- Pennsylvania State UniversityUS1 paper
8 papers
RCPS: Rectified Contrastive Pseudo Supervision for Semi-Supervised Medical Image Segmentation
Xiangyu Zhao, Zengxin Qi, Sheng Wang +4
Medical image segmentation methods are generally designed as fully-supervised to guarantee model performance, which require a significant amount of expert annotated samples that ar…
Quad-Net: Quad-domain Network for CT Metal Artifact Reduction
Zilong Li, Qi Gao, Yaping Wu +5
Metal implants and other high-density objects in patients introduce severe streaking artifacts in CT images, compromising image quality and diagnostic performance. Although various…
SAN-Net: Learning Generalization to Unseen Sites for Stroke Lesion Segmentation with Self-Adaptive Normalization
Weiyi Yu, Zhizhong Huang, Junping Zhang +1
There are considerable interests in automatic stroke lesion segmentation on magnetic resonance (MR) images in the medical imaging field, as stroke is an important cerebrovascular d…
Meta Ordinal Regression Forest for Medical Image Classification with Ordinal Labels
Yiming Lei, Haiping Zhu, Junping Zhang +1
The performance of medical image classification has been enhanced by deep convolutional neural networks (CNNs), which are typically trained with cross-entropy (CE) loss. However, w…
Deep Rank-Consistent Pyramid Model for Enhanced Crowd Counting
Jiaqi Gao, Zhizhong Huang, Yiming Lei +4
Most conventional crowd counting methods utilize a fully-supervised learning framework to establish a mapping between scene images and crowd density maps. They usually rely on a la…
Learning Representation for Clustering via Prototype Scattering and Positive Sampling
Zhizhong Huang, Jie Chen, Junping Zhang +1
Existing deep clustering methods rely on either contrastive or non-contrastive representation learning for downstream clustering task. Contrastive-based methods thanks to negative…