Dense Adaptive Grouping Distillation Network for Multimodal Land Cover Classification With Privileged Modality

土地覆盖 模态(人机交互) 计算机科学 蒸馏 封面(代数) 人工智能 遥感 模式识别(心理学) 机器学习 土地利用 地质学 工程类 机械工程 土木工程 有机化学 化学
作者
Xiao Li,Lin Lei,Caiguang Zhang,Gangyao Kuang
出处
期刊:IEEE Transactions on Geoscience and Remote Sensing [Institute of Electrical and Electronics Engineers]
卷期号:60: 1-14 被引量:20
标识
DOI:10.1109/tgrs.2022.3176936
摘要

Multimodal land cover classification (MLCC) is a fundamental problem in remote sensing interpretation, which can obtain excellent performance on account of the complementary information between the optical and SAR modalities. However, it is usually impossible to obtain multimodal data at the same time, due to the restriction of imaging conditions. When one of the modalities data is completely missing during test phase, classical multimodal learning methods might not be able to handle the MLCC task with privileged modality. In this paper, we propose an efficient Dense Adaptive Grouping Distillation Network (DAGDNet), which learns privileged information from available modalities in the train sets, and improves the classification performance in the test sets when one modality data is scarce. More specifically, to relieve the heterogeneous gaps between different modalities and then transfer the privileged information, we propose an Interactive Gated-based Feature Grouping Module (IG-FGM), which decomposes multimodal features into modalities-shared and modality-specific components to realize the decoupling of multimodal features and grouping distillation. Furthermore, the IG-FGM is inserted into different layers of the "teacher" network to implement progressive blending of multi-modalities. Then, to adaptively highlight the importance of hierarchical features distillation and grouping distillation, we propose a Multi-stage Adaptive Distillation Learning (MS-ADL) strategy so that the weights of different distillation losses are required to change continuously along with the training process. Finally, we evaluate the superior performances of our model on representative co-registered optical and SAR datasets.

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
半阙完成签到,获得积分10
刚刚
1秒前
2秒前
bkagyin的应助被LL采纳,获得10
2秒前
3秒前
缥缈岭南完成签到,获得积分10
3秒前
调皮的善若完成签到,获得积分10
3秒前
危机的发卡完成签到,获得积分10
3秒前
3秒前
4秒前
李爱国的应助被钰宁采纳,获得10
5秒前
NexusExplorer的应助被111采纳,获得10
5秒前
5秒前
霁月发布了新的文献求助10
6秒前
7秒前
523发布了新的文献求助10
7秒前
kds关闭了kds的文献求助
7秒前
zheng发布了新的文献求助10
8秒前
哞的一声学习去了完成签到,获得积分10
9秒前
原儿发布了新的文献求助10
9秒前
酷酷的悒发布了新的文献求助10
10秒前
Chrisding发布了新的文献求助30
10秒前
Owen的应助被珍珠奶茶采纳,获得30
11秒前
12秒前
谭进完成签到,获得积分10
12秒前
12秒前
hzy完成签到 ,获得积分10
12秒前
12秒前
CipherSage的应助被提高采纳,获得10
13秒前
13秒前
Akim的应助被vc采纳,获得10
14秒前
光子完成签到,获得积分10
14秒前
慕青的应助被111采纳,获得10
15秒前
15秒前
NexusExplorer的应助被hanwen采纳,获得10
15秒前
16秒前
Lucas的应助被闪闪严青采纳,获得10
16秒前
稳重傲薇发布了新的文献求助10
16秒前
Ican发布了新的文献求助10
17秒前
温暖绮山发布了新的文献求助10
17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
Handbook of Sport Coaching Research 1000
Orthognathic Surgery - 2 Volume Set 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
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 8192968
求助须知:如何正确求助?哪些是违规求助? 9579365
关于积分的说明 21864799
捐赠科研通 7792532
什么是DOI,文献DOI怎么找? 3437120
关于科研通互助平台的介绍 2560661
邀请新用户注册赠送积分活动 2483960