MCFT: Multimodal Contrastive Fusion Transformer for Classification of Hyperspectral Image and LiDAR Data

高光谱成像 激光雷达 遥感 计算机科学 人工智能 上下文图像分类 融合 图像融合 传感器融合 模式识别(心理学) 计算机视觉 地质学 图像(数学) 语言学 哲学
作者
Yining Feng,Jiarui Jin,Yin Yin,Chuanming Song,Xianghai Wang
出处
期刊:IEEE Transactions on Geoscience and Remote Sensing [Institute of Electrical and Electronics Engineers]
卷期号:62: 1-17 被引量:20
标识
DOI:10.1109/tgrs.2024.3490752
摘要

Multisource remote sensing (RS) image fusion leverages data from various sensors to enhance the accuracy and comprehensiveness of Earth observation. Notably, the fusion of hyperspectral (HS) images and light detection and ranging (LiDAR) data has garnered significant attention due to their complementary features. However, current methods predominantly rely on simplistic techniques such as weight sharing, feature superposition, or feature products, which often fall short of achieving true feature fusion. These methods primarily focus on feature accumulation rather than integrative fusion. The transformer framework, with its self-attention mechanisms, offers potential for effective multimodal data fusion. However, simple linear transformations used in feature extraction may not adequately capture all relevant information. To address these challenges, we propose a novel multimodal contrastive fusion transformer (MCFT). Our approach employs convolutional neural networks (CNNs) for feature extraction from different modalities and leverages transformer networks for advanced fusion. We have modified the basic transformer architecture and propose a double position embedding mode to make it more suitable for RS image processing tasks. We introduce two novel modules: feature alignment module and feature matching module, designed to exploit both paired and unpaired samples. These modules facilitate more effective cross-modal learning by emphasizing the commonalities within the same features and the differences between features from distinct modalities. Experimental evaluations on several publicly available HS-LiDAR datasets demonstrate that proposed method consistently outperforms existing advanced methods. The source code for our approach is available at:https://github.com/SYFYN0317/MCFT.
最长约 10秒,即可获得该文献文件

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
刚刚
科研通AI6.2的应助被LSY采纳,获得10
1秒前
1秒前
vc发布了新的文献求助10
1秒前
xiao完成签到,获得积分10
1秒前
1秒前
2秒前
挚友发布了新的文献求助30
2秒前
该我乐发布了新的文献求助20
2秒前
YY发布了新的文献求助10
2秒前
leajay发布了新的文献求助10
3秒前
3秒前
执着发布了新的文献求助10
3秒前
3秒前
香蕉觅云的应助被孤独的冷安采纳,获得10
4秒前
bingo完成签到,获得积分10
4秒前
科研小牛马完成签到,获得积分10
4秒前
Lindsay完成签到,获得积分10
5秒前
1ce发布了新的文献求助10
5秒前
tester_gater发布了新的文献求助20
5秒前
山竹里发布了新的文献求助10
5秒前
6秒前
神偷奶奶发布了新的文献求助20
6秒前
Orange的应助被123456采纳,获得10
6秒前
6秒前
younglababy发布了新的文献求助10
6秒前
完美世界的应助被小明同学采纳,获得10
8秒前
哈哈哈发布了新的文献求助10
9秒前
9秒前
10秒前
怡然的问晴完成签到,获得积分20
10秒前
科研通AI6.2的应助被韩立采纳,获得10
10秒前
情怀的应助被11采纳,获得10
11秒前
Nole的应助被shushi采纳,获得10
11秒前
打打的应助被QQ采纳,获得10
11秒前
Yangbb完成签到 ,获得积分10
12秒前
zhang发布了新的文献求助10
12秒前
ss完成签到 ,获得积分10
12秒前
Hope完成签到,获得积分10
12秒前
我爱学习完成签到 ,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 1700
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
John McDowells Bildungstheorie 800
八旗制度の研究 600
What Else Can I Tell You?: A Pragmatic Study of English Rhetorical Questions as Discursive and Argumentative Acts 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 8163922
求助须知:如何正确求助?哪些是违规求助? 9558007
关于积分的说明 21743214
捐赠科研通 7754605
什么是DOI,文献DOI怎么找? 3428426
关于科研通互助平台的介绍 2553053
邀请新用户注册赠送积分活动 2473048