TY - JOUR
T1 - Deep Clustering With Intraclass Distance Constraint for Hyperspectral Images
AU - Wei, Xian
AU - Yao, Wei
N1 - Funding Information:
Manuscript received November 20, 2019; revised April 15, 2020 and July 26, 2020; accepted August 9, 2020. Date of publication September 25, 2020; date of current version April 22, 2021. This work was supported in part by the Young Scientists Fund of the National Natural Science Foundation of China under Grant 61602226 and Grant 61806186, and in part by the CAS Pioneer Hundred Talents Program (Type C) under Grant 2017-122. (Jinguang Sun and Wanli Wang contributed equally to this work.) (Corresponding author: Xian Wei.) Jinguang Sun and Wanli Wang are with the School of Electronic and Information Engineering, Liaoning Technical University, Huludao 125105, China (e-mail: [email protected]; [email protected]).
Publisher Copyright:
© 1980-2012 IEEE.
PY - 2021/5
Y1 - 2021/5
N2 - The high dimensionality of hyperspectral images often results in the degradation of clustering performance. Due to the powerful ability of potential feature extraction and nonlinear representation, deep clustering algorithms have become a hot topic in hyperspectral remote sensing. Different tasks often need different features. However, the current deep clustering algorithms generally separate feature extraction from clustering, which results in the extracted features that are not constrained by clustering tasks. Therefore, the features extracted by these algorithms may not be suitable for clustering. To address this issue, we adopt intraclass distance as a constraint condition and proposed an intraclass distance constrained deep clustering algorithm for hyperspectral images. The proposed algorithm propagates the clustering error back to the feature mapping process of the autoencoder network, so as to realize the constraint of clustering objective on feature extraction and make the extracted features more suitable for clustering tasks. In addition, the proposed algorithm simultaneously completes network optimization and clustering, which is more efficient. Experimental results demonstrate the intense competitiveness of the proposed algorithm in comparison with state-of-the-art clustering methods for hyperspectral images.
AB - The high dimensionality of hyperspectral images often results in the degradation of clustering performance. Due to the powerful ability of potential feature extraction and nonlinear representation, deep clustering algorithms have become a hot topic in hyperspectral remote sensing. Different tasks often need different features. However, the current deep clustering algorithms generally separate feature extraction from clustering, which results in the extracted features that are not constrained by clustering tasks. Therefore, the features extracted by these algorithms may not be suitable for clustering. To address this issue, we adopt intraclass distance as a constraint condition and proposed an intraclass distance constrained deep clustering algorithm for hyperspectral images. The proposed algorithm propagates the clustering error back to the feature mapping process of the autoencoder network, so as to realize the constraint of clustering objective on feature extraction and make the extracted features more suitable for clustering tasks. In addition, the proposed algorithm simultaneously completes network optimization and clustering, which is more efficient. Experimental results demonstrate the intense competitiveness of the proposed algorithm in comparison with state-of-the-art clustering methods for hyperspectral images.
KW - Deep learning
KW - hyperspectral images clustering
KW - intraclass distance constraint
KW - low-dimensional (LD) representation
KW - remote sensing
UR - http://www.scopus.com/inward/record.url?scp=85104713993&partnerID=8YFLogxK
U2 - 10.1109/TGRS.2020.3019313
DO - 10.1109/TGRS.2020.3019313
M3 - Journal article
SN - 0196-2892
VL - 59
SP - 4135
EP - 4149
JO - IEEE Transactions on Geoscience and Remote Sensing
JF - IEEE Transactions on Geoscience and Remote Sensing
IS - 5
M1 - 9206066
ER -