Multimodal Informative ViT: Information Aggregation and Distribution for Hyperspectral and LiDAR Classification

计算机科学 冗余(工程) 模式 人工智能 特征学习 相互信息 数据挖掘 模式识别(心理学) 社会科学 社会学 操作系统
作者
Jiaqing Zhang,Jie Liu,Weiying Xie,Yingsan Geng,Daixun Li,Yunsong Li,Karim Seghouane
出处
期刊:Cornell University - arXiv
标识
DOI:10.48550/arxiv.2401.03179
摘要

In multimodal land cover classification (MLCC), a common challenge is the redundancy in data distribution, where irrelevant information from multiple modalities can hinder the effective integration of their unique features. To tackle this, we introduce the Multimodal Informative Vit (MIVit), a system with an innovative information aggregate-distributing mechanism. This approach redefines redundancy levels and integrates performance-aware elements into the fused representation, facilitating the learning of semantics in both forward and backward directions. MIVit stands out by significantly reducing redundancy in the empirical distribution of each modality's separate and fused features. It employs oriented attention fusion (OAF) for extracting shallow local features across modalities in horizontal and vertical dimensions, and a Transformer feature extractor for extracting deep global features through long-range attention. We also propose an information aggregation constraint (IAC) based on mutual information, designed to remove redundant information and preserve complementary information within embedded features. Additionally, the information distribution flow (IDF) in MIVit enhances performance-awareness by distributing global classification information across different modalities' feature maps. This architecture also addresses missing modality challenges with lightweight independent modality classifiers, reducing the computational load typically associated with Transformers. Our results show that MIVit's bidirectional aggregate-distributing mechanism between modalities is highly effective, achieving an average overall accuracy of 95.56% across three multimodal datasets. This performance surpasses current state-of-the-art methods in MLCC. The code for MIVit is accessible at https://github.com/icey-zhang/MIViT.
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
更新
大幅提高文件上传限制,最高150M (2024-4-1)

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
2秒前
行止发布了新的文献求助10
4秒前
深情的迎海完成签到,获得积分10
4秒前
5秒前
上官若男应助老肥采纳,获得10
5秒前
胖儿发布了新的文献求助10
5秒前
7秒前
Naomi-yu发布了新的文献求助10
8秒前
8秒前
8秒前
希望天下0贩的0应助coolkid采纳,获得10
9秒前
kkkay完成签到,获得积分10
11秒前
12秒前
lucilleshen发布了新的文献求助10
13秒前
chaozihao发布了新的文献求助10
14秒前
科研通AI2S应助Sun采纳,获得10
14秒前
12w完成签到,获得积分10
15秒前
受伤幻桃完成签到 ,获得积分10
15秒前
婷婷应助聂慕凝采纳,获得10
18秒前
健康的雁凡完成签到,获得积分10
19秒前
瓜尔佳发布了新的文献求助10
20秒前
20秒前
李健的小迷弟应助TT2022采纳,获得10
21秒前
22秒前
kenna123发布了新的文献求助10
23秒前
23秒前
chaozihao完成签到,获得积分10
23秒前
cnspower发布了新的文献求助10
24秒前
07发布了新的文献求助10
27秒前
叶问夏完成签到 ,获得积分10
27秒前
28秒前
麦田里的守望者完成签到,获得积分10
29秒前
yuan完成签到,获得积分20
31秒前
31秒前
李健应助zxfaaaaa采纳,获得30
32秒前
彭于晏应助xu采纳,获得10
32秒前
英姑应助corner采纳,获得10
33秒前
鲤鱼冬灵完成签到,获得积分10
35秒前
38秒前
41秒前
高分求助中
Evolution 10000
Becoming: An Introduction to Jung's Concept of Individuation 600
Ore genesis in the Zambian Copperbelt with particular reference to the northern sector of the Chambishi basin 500
A new species of Coccus (Homoptera: Coccoidea) from Malawi 500
A new species of Velataspis (Hemiptera Coccoidea Diaspididae) from tea in Assam 500
PraxisRatgeber: Mantiden: Faszinierende Lauerjäger 500
The Kinetic Nitration and Basicity of 1,2,4-Triazol-5-ones 440
热门求助领域 (近24小时)
化学 医学 生物 材料科学 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 基因 遗传学 催化作用 物理化学 免疫学 量子力学 细胞生物学
热门帖子
关注 科研通微信公众号,转发送积分 3164075
求助须知:如何正确求助?哪些是违规求助? 2814831
关于积分的说明 7906671
捐赠科研通 2474391
什么是DOI,文献DOI怎么找? 1317493
科研通“疑难数据库(出版商)”最低求助积分说明 631797
版权声明 602198