Xu Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Xu Zhang has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Donglin Di
Harbin Institute of Technology, Harbin, China
1 shared publication Guangsheng Chen
College of Information and Computer Engineering, Northeast Forestry University, Harbin, China
1 shared publication- Houbing Song
University of Maryland, Baltimore County (UMBC)
1 shared publication Jian Wang
Aerospace Information Research Institute, Chinese Academy of Sciences (CAS), Beijing, China
1 shared publication- Weipeng Jing
College of Computer and Control Engineering, Northeast Forestry University, Harbin 150040, China
1 shared publication
Latest Publications
- 22 March 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 19 (1545598X) , 1-5
Binary Neural Network for Multispectral Image Classification
Compared with traditional images, multispectral images (MSIs) contain more spectral bands and higher data dimensions. The existing MSI classification model has high computational complexity and consumes a lot of computing resources. In this letter, we propose a lightweight multispectral classification method named CABNN based on binary neural networks (BNNs) to effectively have a trade-off between model performance and computational cost. First, we modify and binarize the MobileNetV1 network and add almost computation-free shortcuts to enhance the expressive capability. Secondly, since the BNN is sensitive to the distribution of activation functions, we introduce RPReLU with learnable coefficients to automatically adjust activation distribution at almost no extra cost. Lastly, considering that MSIs have multiple channels, we utilize an efficient channel attention (ECA) module to assign different weights to each channel to concentrate on crucial features and suppress insignificant features. We conduct experiments on four public MSI datasets, including NaSC-TG2, EuroSAT, GID Fine land-cover classification, and UC Merced Land Use. Extensive experiments demonstrate that the proposed CABNN has higher efficiency and better comprehensive performance than the state-of-the-art methods across the board.
- 22 March 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 19 (1545598X) , 1-5
Binary Neural Network for Multispectral Image Classification
Compared with traditional images, multispectral images (MSIs) contain more spectral bands and higher data dimensions. The existing MSI classification model has high computational complexity and consumes a lot of computing resources. In this letter, we propose a lightweight multispectral classification method named CABNN based on binary neural networks (BNNs) to effectively have a trade-off between model performance and computational cost. First, we modify and binarize the MobileNetV1 network and add almost computation-free shortcuts to enhance the expressive capability. Secondly, since the BNN is sensitive to the distribution of activation functions, we introduce RPReLU with learnable coefficients to automatically adjust activation distribution at almost no extra cost. Lastly, considering that MSIs have multiple channels, we utilize an efficient channel attention (ECA) module to assign different weights to each channel to concentrate on crucial features and suppress insignificant features. We conduct experiments on four public MSI datasets, including NaSC-TG2, EuroSAT, GID Fine land-cover classification, and UC Merced Land Use. Extensive experiments demonstrate that the proposed CABNN has higher efficiency and better comprehensive performance than the state-of-the-art methods across the board.