.png){kind=icon}
返回
Active Deep Feature Extraction for Hyperspectral Image Classification Based on Adversarial Learning
.png){kind=icon}
PRE
AI
DOI：10.1109/LGRS.2022.3186493.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
The issues of spectral redundancy and limited training samples hinder the widespread application and development of hyperspectral images. In this letter, a novel active deep feature extraction scheme is proposed by incorporating both representative and informative measurement. First, an adversarial autoencoder (AAE) is modified to suit the classification task with deep feature extraction. Dictionary learning and a multivariance and distributional distance (MVDD) measure are then introduced to choose the most valuable candidate training samples, where we use the limited labeled samples to obtain a high classification accuracy. Comparative experiments with the proposed querying strategy were carried out with two hyperspectral datasets. The experimental results obtained with the two datasets demonstrate that the proposed scheme is superior to the others. With this method, the unstable increase in accuracy is eliminated by incorporating both informative and representative measurement.
Keyword:
Training
Hyperspectral imaging
Feature extraction
Dictionaries
Uncertainty
Image classification
Deep learning
Active learning
adversarial autoencoder (AAE)
hyperspectral image classification
sparse representation
期刊
IF:
16.4
论文数:
1.0W
被引数:
5.1K
机构
引用论文
Visual deficits and cognitive assessment of multiple sclerosis: confounder, correlate, or both?多发性硬化症的视觉缺陷和认知评估: 混杂，相关，或两者兼而有之？
PREAI
分享收藏Active Learning With Convolutional Neural Networks for Hyperspectral Image Classification Using a New Bayesian Approach使用卷积神经网络的主动学习，使用新的贝叶斯方法进行高光谱图像分类
PREAI
分享收藏Anti-Yo Antibody Uptake and Interaction with Its Intracellular Target Antigen Causes Purkinje Cell Death in Rat Cerebellar Slice Cultures: A Possible Mechanism for Paraneoplastic Cerebellar Degeneration in Humans with Gynecological or Breast Cancers抗Yo抗体的摄取及其与细胞内靶抗原的相互作用导致大鼠小脑切片培养物中的浦肯野细胞死亡: 妇科或乳腺癌患者副肿瘤性小脑变性的可能机制.png)
PLOS ONE
OAAI
PLOS ONEIF0
OAAI分享收藏Batch Mode Active Sampling Based on Marginal Probability Distribution Matching基于边际概率分布匹配的批量模式主动抽样
OAAI
OAAI分享收藏
查看更多内容