2 code implementations • 20 Dec 2021 • Haigen Hu, Leizhao Shen, Qiu Guan, Xiaoxin Li, Qianwei Zhou, Su Ruan
In this paper, a novel segmentation scheme is proposed for the infections of COVID-19 by enhancing supervised information and fusing multi-scale feature maps of different levels based on the encoder-decoder architecture.
1 code implementation • 17 Dec 2021 • Haigen Hu, Aizhu Liu, Qiu Guan, Xiaoxin Li, ShengYong Chen, Qianwei Zhou
To enhance the nonlinearity of neural networks and increase their mapping abilities between the inputs and response variables, activation functions play a crucial role to model more complex relationships and patterns in the data.
no code implementations • 6 Oct 2020 • Qianwei Zhou, Yuhang Chen, Baoqing Li, Xiaoxin Li, Chen Zhou, Jingchang Huang, Haigen Hu
Although deep learning has achieved remarkable successes over the past years, few reports have been published about applying deep neural networks to Wireless Sensor Networks (WSNs) for image targets recognition where data, energy, computation resources are limited.
no code implementations • 6 Feb 2020 • Qianwei Zhou, Peng Tao, Xiaoxin Li, Sheng-Yong Chen, Fan Zhang, Haigen Hu
Shape illustration images (SIIs) are common and important in describing the cross-sections of industrial products.
no code implementations • 17 Nov 2019 • Qianwei Zhou, Chen Zhou, Haigen Hu, Yuhang Chen, Sheng-Yong Chen, Xiaoxin Li
Single image inverse problem is a notoriously challenging ill-posed problem that aims to restore the original image from one of its corrupted versions.