Cross-Domain Collaborative Learning via Cluster Canonical Correlation Analysis and Random Walker for Hyperspectral Image Classification

• Published in: IEEE transactions on geoscience and remote sensing Vol. 57; no. 6; pp. 3952 - 3966
• Main Authors: Qin, Yao, Bruzzone, Lorenzo, Li, Biao, Ye, Yuanxin
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.06.2019; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Adaptation; Algorithms; Classification; Classifiers; Cluster canonical correlation analysis (C-CCA); Clustering algorithms; Clusters; Collaborative learning; Correlation; Correlation analysis; cross-domain collaborative learning (CDCL); Domains; Feature extraction; heterogeneous domain adaptation (HDA); hyperspectral image (HSI) classification; Hyperspectral imaging; Image classification; Image edge detection; Image processing; Image segmentation; Iterative methods; Learning; Machine learning; Manifolds; Probability theory; random walker (RW); remote sensing; Training
• ISSN: 0196-2892; 1558-0644
• DOI: 10.1109/TGRS.2018.2889195

This paper introduces a novel heterogeneous domain adaptation (HDA) method for hyperspectral image (HSI) classification with a limited amount of labeled samples in both domains. The method is achieved in the way of cross-domain collaborative learning (CDCL), which is addressed via cluster canonical correlation analysis (C-CCA) and random walker (RW) algorithms. To be specific, the proposed CDCL method is an iterative process of three main components, i.e., RW-based pseudolabeling, cross-domain learning via C-CCA, and final classification based on extended RW (ERW) algorithm. First, given the initially labeled target samples as the training set (TS), the RW-based pseudolabeling is employed to update TS and extract target clusters (TCs) by fusing the segmentation results obtained by RW and ERW classifiers. Second, cross-domain learning via C-CCA is applied using labeled source samples and TCs. The unlabeled target samples are then classified with the estimated probability maps using the model trained in the projected correlation subspace. The newly estimated probability map and TS are used for updating TS again via RW-based pseudolabeling. Finally, when the iterative process converges, the result obtained by the ERW classifier using the final TS and estimated probability maps is regarded as the final classification map. Experimental results on four real HSIs demonstrate that the proposed method can achieve better performance compared with the state-of-the-art HDA and ERW methods.