Search Results for author: Junyang Chen

Found 8 papers, 2 papers with code

A Unified Joint Maximum Mean Discrepancy for Domain Adaptation

no code implementations25 Jan 2021 Wei Wang, Baopu Li, Shuhui Yang, Jing Sun, Zhengming Ding, Junyang Chen, Xiao Dong, Zhihui Wang, Haojie Li

From the revealed unified JMMD, we illustrate that JMMD degrades the feature-label dependence (discriminability) that benefits to classification, and it is sensitive to the label distribution shift when the label kernel is the weighted class conditional one.

Domain Adaptation

Efficient Medical Image Segmentation with Intermediate Supervision Mechanism

no code implementations15 Nov 2020 Di Yuan, Junyang Chen, Zhenghua Xu, Thomas Lukasiewicz, Zhigang Fu, Guizhi Xu

However, U-Net is mainly engaged in segmentation, and the extracted features are also targeted at segmentation location information, and the input and output are different.

Medical Image Segmentation Semantic Segmentation

SAG-GAN: Semi-Supervised Attention-Guided GANs for Data Augmentation on Medical Images

no code implementations15 Nov 2020 Chang Qi, Junyang Chen, Guizhi Xu, Zhenghua Xu, Thomas Lukasiewicz, Yang Liu

We first generate MRI images on limited datasets, then we trained three popular classification models to get the best model for tumor classification.

Classification Data Augmentation +2

Joint Self-Attention and Scale-Aggregation for Self-Calibrated Deraining Network

1 code implementation6 Aug 2020 Cong Wang, Yutong Wu, Zhixun Su, Junyang Chen

In the field of multimedia, single image deraining is a basic pre-processing work, which can greatly improve the visual effect of subsequent high-level tasks in rainy conditions.

Single Image Deraining

DCSFN: Deep Cross-scale Fusion Network for Single Image Rain Removal

no code implementations3 Aug 2020 Cong Wang, Xiaoying Xing, Zhixun Su, Junyang Chen

Further, we design an inner-scale connection block to utilize the multi-scale information and features fusion way between different scales to improve rain representation ability and we introduce the dense block with skip connection to inner-connect these blocks.

Rain Removal

D2D-Enabled Data Sharing for Distributed Machine Learning at Wireless Network Edge

no code implementations28 Jan 2020 Xiaoran Cai, Xiaopeng Mo, Junyang Chen, Jie Xu

Mobile edge learning is an emerging technique that enables distributed edge devices to collaborate in training shared machine learning models by exploiting their local data samples and communication and computation resources.

Cannot find the paper you are looking for? You can Submit a new open access paper.