Zekuan Yu — accepted AI-conference papers

2024

SSHNN: Semi-Supervised Hybrid NAS Network for Echocardiographic Image Segmentation

Renqi Chen, Jingjing Luo, Fan Nian, Yuhui Cen, Yiheng Peng, Zekuan Yu

ICASSP 2024accepted

Accurate medical image segmentation especially for echocardiographic images with unmissable noise requires elaborate network design. Compared with manual design, Neural Architecture Search (NAS) realizes better segmentation results due to larger search space and automatic optimization, but most of t…

Cited by 0 Source ↗Scholar ↗

2021

PML: Progressive Margin Loss for Long-Tailed Age Classification

Zongyong Deng, Hao Liu, Yaoxing Wang, Chenyang Wang, Zekuan Yu, Xuehong Sun

CVPR 2021poster

In this paper, we propose a progressive margin loss (PML) approach for unconstrained facial age classification. Conventional methods make strong assumption on that each class owns adequate instances to outline its data distribution, likely leading to bias prediction where the training samples are sp…

Cited by 83 PDF ↗code ↗Scholar ↗