1. EMFNet: Enhanced Multisource Fusion Network for Land Cover Classification
- Author
-
Chengxiang Li, Behnood Rasti, and Renlong Hang
- Subjects
Atmospheric Science ,010504 meteorology & atmospheric sciences ,Computer science ,Convolutional neural network (CNN) ,Geophysics. Cosmic physics ,Feature extraction ,0211 other engineering and technologies ,feature fusion module ,02 engineering and technology ,Land cover ,01 natural sciences ,Convolutional neural network ,multisource fusion ,Computers in Earth Sciences ,Layer (object-oriented design) ,TC1501-1800 ,021101 geological & geomatics engineering ,0105 earth and related environmental sciences ,Fusion ,QC801-809 ,business.industry ,feature tuning module ,Hyperspectral imaging ,Pattern recognition ,Ocean engineering ,Feature (computer vision) ,Fuse (electrical) ,Artificial intelligence ,business - Abstract
Feature extraction and fusion are two critical issues for the task of multisource classification. In this article, we propose an enhanced multisource fusion network (EMFNet) to address them in an end-to-end framework. Specifically, two convolutional neural networks are employed to extract features from two different sources. Each network is mainly comprised of three convolutional layers. For each convolutional layer, feature tuning modules are designed to enhance the extracted feature of one source by taking advantage of the other source. After getting the features of two sources, a weighted summation method is used to fuse them. Considering that fusion weights should vary for different inputs, a feature fusion module is designed to achieve this goal. In order to test the performance of our proposed EMFNet, we compare it with state-of-the-art fusion models, including the traditional models and the deep-learning-based models, on two real datasets. Experimental results show that the EMFNet can achieve competitive classification results in comparison with them.
- Published
- 2021