A Novel Hyperspectral Image Classification Model Using Bole Convolution With Three-Direction Attention Mechanism: Small Sample and Unbalanced Learning

计算机科学 高光谱成像 模式识别(心理学) 人工智能 冗余(工程) 卷积(计算机科学) 背景(考古学) 支持向量机 人工神经网络 数据挖掘 古生物学 生物 操作系统
作者
Weiwei Cai,Xin Ning,Guoxiong Zhou,Xiao Bai,Yizhang Jiang,Wei Li,Pengjiang Qian
出处
期刊:IEEE Transactions on Geoscience and Remote Sensing [Institute of Electrical and Electronics Engineers]
卷期号:61: 1-17 被引量:28
标识
DOI:10.1109/tgrs.2022.3201056
摘要

Currently, the use of rich spectral and spatial information of hyperspectral images (HSIs) to classify ground objects is a research hotspot. However, the classification ability of existing models is significantly affected by its high data dimensionality and massive information redundancy. Therefore, we focus on the elimination of redundant information and the mining of promising features and propose a novel Bole convolution (BC) neural network with a tandem three-direction attention (TDA) mechanism (BTA-Net) for the classification of HSI. A new BC is proposed for the first time in this algorithm, whose core idea is to enhance effective features and eliminate redundant features through feature punishment and reward strategies. Considering that traditional attention mechanisms often assign weights in a one-direction manner, leading to a loss of the relationship between the spectra, a novel three-direction (horizontal, vertical, and spatial directions) attention mechanism is proposed, and an addition strategy and a maximization strategy are used to jointly assign weights to improve the context sensitivity of spatial–spectral features. In addition, we also designed a tandem TDA mechanism module and combined it with a multiscale BC output to improve classification accuracy and stability even when training samples are small and unbalanced. We conducted scene classification experiments on four commonly used hyperspectral datasets to demonstrate the superiority of the proposed model. The proposed algorithm achieves competitive performance on small samples and unbalanced data, according to the results of comparison and ablation experiments. The source code for BTA-Net can be found at https://github.com/vivitsai/BTA-Net .

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
1秒前
彭于晏的应助被缺粥采纳,获得10
2秒前
2秒前
2秒前
cici完成签到,获得积分10
3秒前
3秒前
羊腿完成签到 ,获得积分10
4秒前
TGJ发布了新的文献求助10
4秒前
慕青的应助被ssswww采纳,获得10
4秒前
1210xi完成签到,获得积分10
5秒前
世间安得双全法完成签到,获得积分0
6秒前
Maestro_S完成签到,获得积分0
6秒前
6秒前
6秒前
weqhdgjfk完成签到,获得积分10
6秒前
无头苍蝇完成签到,获得积分10
6秒前
躺平青年阿俊完成签到,获得积分10
6秒前
7秒前
st完成签到,获得积分10
7秒前
jzhou65完成签到,获得积分10
8秒前
8秒前
sense发布了新的文献求助10
9秒前
花花完成签到,获得积分10
9秒前
9秒前
9秒前
CC66发布了新的文献求助10
10秒前
10秒前
捞鱼完成签到,获得积分10
11秒前
11秒前
11秒前
ssswww完成签到,获得积分10
11秒前
张志辉完成签到,获得积分10
11秒前
薛小飞发布了新的文献求助10
12秒前
dent强完成签到,获得积分10
12秒前
无限紫槐发布了新的文献求助10
13秒前
ddd发布了新的文献求助10
13秒前
古语发布了新的文献求助10
13秒前
66发布了新的文献求助10
14秒前
烟花的应助被cxy采纳,获得10
14秒前
Shirly完成签到,获得积分10
14秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 2000
Sex, Aging, and Death in a Medieval Medical Compendium: Trinity College Cambridge MS R.14.52, Its Texts, Language, and Scribe 500
高分子基功能界面水蒸发材料与应用研究 500
外场增强的水汽发电研究 500
基于结构调控的功能化水诱导发电材料与器件研究 500
基于界面调控的高效湿气发电材料与器件研究 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8190478
求助须知:如何正确求助?哪些是违规求助? 9577686
关于积分的说明 21853808
捐赠科研通 7789496
什么是DOI,文献DOI怎么找? 3436407
关于科研通互助平台的介绍 2560235
邀请新用户注册赠送积分活动 2483054