Collaborative Active Learning Based on Improved Capsule Networks for Hyperspectral Image Classification

计算机科学 人工智能 高光谱成像 水准点(测量) 机器学习 注释 上下文图像分类 人工神经网络 深度学习 模式识别(心理学) 数据挖掘 图像(数学) 大地测量学 地理
作者
Heng Wang,Liguo Wang
出处
期刊:IEEE Transactions on Geoscience and Remote Sensing [Institute of Electrical and Electronics Engineers]
卷期号:61: 1-26 被引量:2
标识
DOI:10.1109/tgrs.2023.3309269
摘要

For hyperspectral image classification (HIC) tasks, most uncertainty-based active learning (AL) methods only consider the uncertainty, without considering the diversity of actively selected samples and the budget of expert labeling. In this paper, we propose a collaborative active learning (CAL) framework to address this problem. The proposed framework consists of two well-designed base classifiers and an ingenious CAL scheme that takes into account both the uncertainty and diversity of actively selected samples and the cost of expert annotation. Specifically, get benefit from the capsule networks’ ability to accurately identify and locate features, we design two improved capsule networks. For these two networks, we call the first CapsViT (Capsule Vision Transformer), which introduces Vision Transformer (ViT) into the capsule network (CapsNet) to learn the global relationship between the capsule features. We call the second CapsGLOM (Capsule GLOM), the basic structure of this network is derived from the GLOM system proposed by Geoffrey Hinton, we learn from the way CapsNet constructs the primary capsules to improve its implementation details. CapsViT and CapsGLOM are used as the two base classifiers in the proposed CAL framework to select the most informative samples according to the CAL scheme under the premise of fully considering the cost of expert annotation. Experimental results on four benchmark hyperspectral image data sets show that our proposed CAL framework can achieve satisfactory classification results. At the same time, compared with other advanced deep models, our proposed CapsViT and CapsGLOM are also competitive in the supervised HIC tasks. The source code can be available online (https://github.com/swiftest/CAL).
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
包子发布了新的文献求助10
刚刚
orixero应助瑞瑞采纳,获得10
刚刚
金22发布了新的文献求助10
1秒前
酷波er应助PanCiro采纳,获得10
1秒前
1秒前
rabbitbeibei完成签到,获得积分10
1秒前
噢锦完成签到,获得积分10
1秒前
活泼纲发布了新的文献求助10
1秒前
天天快乐应助bjr采纳,获得10
1秒前
liuliu发布了新的文献求助10
1秒前
rainhowk完成签到,获得积分10
2秒前
YellowStar发布了新的文献求助10
2秒前
Zoe发布了新的文献求助10
3秒前
3秒前
duoduo发布了新的文献求助10
4秒前
量子星尘发布了新的文献求助10
4秒前
哇哈哈发布了新的文献求助10
4秒前
4秒前
4秒前
光之美少女完成签到,获得积分10
5秒前
天空xka完成签到 ,获得积分10
5秒前
完美世界应助Mr.Su采纳,获得10
6秒前
在水一方应助十六采纳,获得10
6秒前
7秒前
情怀应助Vicki采纳,获得10
7秒前
sakiecon完成签到,获得积分10
7秒前
文艺谷蓝完成签到,获得积分10
8秒前
程琛发布了新的文献求助10
8秒前
LQ完成签到,获得积分10
9秒前
小小怪发布了新的文献求助10
9秒前
星河发布了新的文献求助10
10秒前
10秒前
领导范儿应助Ace采纳,获得10
11秒前
11秒前
哇哈哈完成签到,获得积分10
12秒前
a1049ni发布了新的文献求助10
12秒前
12秒前
YellowStar完成签到,获得积分10
12秒前
Ava应助飞天意面采纳,获得10
13秒前
jeitt完成签到,获得积分10
13秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
Technical Brochure TB 814: LPIT applications in HV gas insulated switchgear 1000
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
Picture Books with Same-sex Parented Families: Unintentional Censorship 500
Nucleophilic substitution in azasydnone-modified dinitroanisoles 500
不知道标题是什么 500
A Preliminary Study on Correlation Between Independent Components of Facial Thermal Images and Subjective Assessment of Chronic Stress 500
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 3970394
求助须知:如何正确求助?哪些是违规求助? 3515139
关于积分的说明 11177107
捐赠科研通 3250335
什么是DOI,文献DOI怎么找? 1795254
邀请新用户注册赠送积分活动 875732
科研通“疑难数据库(出版商)”最低求助积分说明 805054