期刊
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
卷 14, 期 -, 页码 8180-8192出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/JSTARS.2021.3103176
关键词
Feature extraction; Image classification; Hyperspectral imaging; Convolutional neural networks; Training; Kernel; Deep learning; Convolutional neural network (CNN); dual-branch feature fusion (DBFM); hyperspectral image (HSI) classification; multiscale feature extraction (MSFE) module; shuffle attention block
类别
资金
- National Natural Science Foundation of China [62071168]
- National Key Research and Development Program of China [2018YFC1508106]
- Fundamental Research Funds for the Central Universities of China [B200202183]
- China Postdoctoral Science Foundation [2021M690885]
A novel multiscale dual-branch feature fusion and attention network was proposed to address feature extraction singleness and rough feature fusion process in existing methods, achieving improved classification performance by extracting spatial-spectral features at a granular level and utilizing a dual-branch feature fusion interactive module. Additionally, the introduction of a shuffle attention mechanism further enhanced the adaptive weighting of spatial and spectral features, leading to improved classification performance over state-of-the-art methods on benchmark datasets.
Recently, hyperspectral image classification based on deep learning has achieved considerable attention. Many convolutional neural network classification methods have emerged and exhibited superior classification performance. However, most methods focus on extracting features by using fixed convolution kernels and layer-wise representation, resulting in feature extraction singleness. Additionally, the feature fusion process is rough and simple. Numerous methods get accustomed to fusing different levels of features by stacking modules hierarchically, which ignore the combination of shallow and deep spectral-spatial features. In order to overcome the preceding issues, a novel multiscale dual-branch feature fusion and attention network is proposed. Specifically, we design a multiscale feature extraction (MSFE) module to extract spatial-spectral features at a granular level and expand the range of receptive fields, thereby enhancing the MSFE ability. Subsequently, we develop a dual-branch feature fusion interactive module that integrates the residual connection's feature reuse property and the dense connection's feature exploration capability, obtaining more discriminative features in both spatial and spectral branches. Additionally, we introduce a novel shuffle attention mechanism that allows for adaptive weighting of spatial and spectral features, further improving classification performance. Experimental results on three benchmark datasets demonstrate that our model outperforms other state-of-the-art methods while incurring the lower computational cost.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据