计算机科学
核(代数)
判别式
卷积(计算机科学)
卷积神经网络
模式识别(心理学)
计算复杂性理论
高光谱成像
人工智能
特征提取
特征(语言学)
频道(广播)
上下文图像分类
算法
图像(数学)
人工神经网络
数学
计算机网络
语言学
哲学
组合数学
作者
Lin Bai,Cuiling Li,Qingxin Liu,Lin Bai,James E. Fowler
出处
期刊:IEEE Geoscience and Remote Sensing Letters
[Institute of Electrical and Electronics Engineers]
日期:2023-01-01
卷期号:20: 1-5
被引量:3
标识
DOI:10.1109/lgrs.2023.3285208
摘要
Convolutional networks have been widely used for the classification of hyperspectral images; however, such networks are notorious for their large number of trainable parameters and high computational complexity. Additionally, traditional convolution-based methods are typically implemented as a simple cascade of a number of convolutions using a single-scale convolution kernel. In contrast, a lightweight multiscale convolutional network is proposed, capitalizing on feature extraction at multiple scales in parallel branches followed by feature fusion. In this approach, 2D depthwise convolution is used instead of conventional convolution in order to reduce network complexity without sacrificing classification accuracy. Furthermore, multiscale channel attention is also employed to selectively exploit discriminative capability across various channels. To do so, multiple 1D convolutions with varying kernel sizes provide channel attention at multiple scales, again with the goal of minimizing network complexity. Experimental results reveal that the proposed network not only outperforms other competing lightweight classifiers in terms of classification accuracy but also exhibits a lower number of parameters as well as significantly less computational cost.
科研通智能强力驱动
Strongly Powered by AbleSci AI