Decoupled Knowledge Distillation via Spatial Feature Blurring for Hyperspectral Image Classification

计算机科学 高光谱成像 人工智能 模式识别(心理学) 变压器 卷积神经网络 像素 骨干网 嵌入 人工神经网络 计算机网络 物理 量子力学 电压
作者
Wen Xie,ZheZhe Zhang,Licheng Jiao,Jin Wang
出处
期刊:IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing [Institute of Electrical and Electronics Engineers]
卷期号:17: 8938-8955 被引量:2
标识
DOI:10.1109/jstars.2024.3383854
摘要

It is well known that distillation learning has the ability to enhance the performance of a light (student) model by transferring knowledge from a heavy (teacher) model, without incurring additional computational and storage costs. This article proposes an improved decoupled knowledge distillation (DKD) strategy for hyperspectral image (HSI) classification. A spatial feature blurring (SFB) module is designed to improve the classification performance of the student network when using DKD strategy. The SFB module utilizes randomly initialized two-dimensional standard normal distribution tensors to blur the spatial features of HSI, which increases the complexity of the data. This aligns with the characteristics of DKD, which transfers more useful knowledge under the condition of sample complexity. To effectively transfer knowledge, this article proposes a robust teacher network named the dual-branch spatial transformer-spectral transformer (DBSTST) network. This network describes the spatial and spectral long-range dependencies of HSI, addressing the limitations of convolutional neural networks (CNNs) in capturing only local features due to their fixed receptive fields. More specifically, the DBSTST network adopts spatial transformer-spectral transformer (STST) which is composed of a parallel spatial-spectral multi-head self-attention (PS2MHSA) module, aiming to describe pixel-level spatial long-range dependencies and spectral correlations in HSI. Simultaneously, the introduction of spatial-spectral positional embedding into PS2MHSA enhances positional awareness. We demonstrated the effectiveness of our proposed method on four publicly available HSI datasets. The student network achieves classification performance improvement and surpasses some other networks. Moreover, when compared to state-of-the-art classification methods, the DBSTST network also exhibits significant improvements in classification performance.
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
PDF的下载单位、IP信息已删除 (2025-6-4)

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
量子星尘发布了新的文献求助10
2秒前
4秒前
华仔应助机灵飞阳采纳,获得10
5秒前
潘善若发布了新的文献求助10
5秒前
6秒前
陈少华完成签到 ,获得积分10
6秒前
下一秒发布了新的文献求助10
7秒前
杨乃彬完成签到,获得积分10
7秒前
取名叫做利完成签到,获得积分10
8秒前
赘婿应助喻义梅采纳,获得10
9秒前
小二郎应助小门采纳,获得10
10秒前
ll发布了新的文献求助10
13秒前
正直的鸿完成签到,获得积分10
18秒前
19秒前
万能图书馆应助高贵梦露采纳,获得10
20秒前
momo发布了新的文献求助10
22秒前
传奇3应助boltos采纳,获得10
23秒前
23秒前
24秒前
要减肥笑阳完成签到 ,获得积分10
25秒前
全若之发布了新的文献求助10
30秒前
Jasper应助momo采纳,获得10
32秒前
Kasom完成签到 ,获得积分10
39秒前
顺利一德完成签到,获得积分20
40秒前
香蕉觅云应助Afaq采纳,获得10
40秒前
40秒前
40秒前
manman完成签到,获得积分10
41秒前
41秒前
哈哈哈完成签到,获得积分10
41秒前
YamDaamCaa应助科研通管家采纳,获得30
42秒前
42秒前
领导范儿应助科研通管家采纳,获得10
42秒前
香蕉觅云应助科研通管家采纳,获得10
42秒前
42秒前
大个应助科研通管家采纳,获得10
42秒前
czh应助科研通管家采纳,获得20
42秒前
科研通AI2S应助科研通管家采纳,获得10
42秒前
酷波er应助科研通管家采纳,获得10
42秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
‘Unruly’ Children: Historical Fieldnotes and Learning Morality in a Taiwan Village (New Departures in Anthropology) 400
Indomethacinのヒトにおける経皮吸収 400
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 370
基于可调谐半导体激光吸收光谱技术泄漏气体检测系统的研究 350
Robot-supported joining of reinforcement textiles with one-sided sewing heads 320
热门求助领域 (近24小时)
化学 材料科学 医学 生物 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 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3989263
求助须知:如何正确求助?哪些是违规求助? 3531418
关于积分的说明 11253814
捐赠科研通 3270066
什么是DOI,文献DOI怎么找? 1804884
邀请新用户注册赠送积分活动 882084
科研通“疑难数据库(出版商)”最低求助积分说明 809136