Binary Neural Network for Multispectral Image Classification
- 22 March 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 19 (1545598X) , 1-5
Abstract
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.Keywords
Funding Information
- National Natural Science Foundation of China (32171777)
- Fundamental Research Funds for the Central Universities (2572017PZ04)
- Heilongjiang Province Applied Technology Research and Development Program Major Project (GA20A301)
This publication has 16 references indexed in Scilit:
- ReActNet: Towards Precise Binary Neural Network with Generalized Activation Functions2020
- Forward and Backward Information Retention for Accurate Binary Neural Networks2020
- Land-cover classification with high-resolution remote sensing images using transferable deep modelsRemote Sensing of Environment, 2020
- Distillation-Based Training for Multi-Exit Architectures2019
- EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover ClassificationIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2019
- Bi-Real Net: Enhancing the Performance of 1-Bit CNNs with Improved Representational Capability and Advanced Training Algorithm2018
- Mapping Global Bamboo Forest Distribution Using Multisource Remote Sensing DataIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2018
- Channel Pruning for Accelerating Very Deep Neural Networks2017
- XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks2016
- Bag-of-visual-words and spatial extensions for land-use classification2010