A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Collaborative Active and Semisupervised Learning for Hyperspectral Remote Sensing Image Classification
Hyperspectral image classification is a challenging problem. Among existing approaches to addressing this problem, the active learning (AL) and semisupervised learning (SSL) techniques have attracted much attention in recent years. AL usually involves a labor-intensive human-labeling process while SSL, although avoiding human labeling by assigning pseudolabels to unlabeled data, may introduce incorrect pseudolabels and thus deteriorate classification performance. To overcome these drawbacks, a novel approach named collaborative active and semisupervised learning (CASSL) is proposed in this paper. CASSL combines AL and SSL to invoke a collaborative labeling process by both human experts and classifiers. Specifically, an AL-based pseudolabel verification procedure is performed for gradually improving the pseudolabeling accuracy to facilitate SSL. Meanwhile, only those unlabeled data with low pseudolabeling confidence in SSL will become the query candidates in AL. We evaluate the performance of CASSL on three hyperspectral data sets and compare it with that of two state-of-the-art hyperspectral image classification methods. Experimental results reveal the superiority of CASSL.
Collaborative Active and Semisupervised Learning for Hyperspectral Remote Sensing Image Classification
Hyperspectral image classification is a challenging problem. Among existing approaches to addressing this problem, the active learning (AL) and semisupervised learning (SSL) techniques have attracted much attention in recent years. AL usually involves a labor-intensive human-labeling process while SSL, although avoiding human labeling by assigning pseudolabels to unlabeled data, may introduce incorrect pseudolabels and thus deteriorate classification performance. To overcome these drawbacks, a novel approach named collaborative active and semisupervised learning (CASSL) is proposed in this paper. CASSL combines AL and SSL to invoke a collaborative labeling process by both human experts and classifiers. Specifically, an AL-based pseudolabel verification procedure is performed for gradually improving the pseudolabeling accuracy to facilitate SSL. Meanwhile, only those unlabeled data with low pseudolabeling confidence in SSL will become the query candidates in AL. We evaluate the performance of CASSL on three hyperspectral data sets and compare it with that of two state-of-the-art hyperspectral image classification methods. Experimental results reveal the superiority of CASSL.
Collaborative Active and Semisupervised Learning for Hyperspectral Remote Sensing Image Classification
Lunjun Wan (author) / Ke Tang / Mingzhi Li / Yanfei Zhong / Qin, A. K
2015
Article (Journal)
English
Local classification TIB:
770/3710/5670
BKL:
38.03
Methoden und Techniken der Geowissenschaften
/
74.41
Luftaufnahmen, Photogrammetrie
Semisupervised Self-Learning for Hyperspectral Image Classification
| Online Contents | 2013
A Novel Semisupervised Active-Learning Algorithm for Hyperspectral Image Classification
| Online Contents | 2017
Semisupervised Neural Networks for Efficient Hyperspectral Image Classification
| Online Contents | 2010
Semisupervised Discriminative Locally Enhanced Alignment for Hyperspectral Image Classification
| Online Contents | 2013