Jointly Informative and Manifold Structure Representative Sampling Based Active Learning for Remote Sensing Image Classification

• Published in: IEEE transactions on geoscience and remote sensing Vol. 54; no. 11; pp. 6803 - 6817
• Main Authors: Samat, Alim, Gamba, Paolo, Sicong Liu, Peijun Du, Abuduwaili, Jilili
• Format: Journal Article
• Language: English
• Published: New York IEEE 01-11-2016; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Active learning (AL); Delaunay triangulation nets (DTNs); Discriminant analysis; image classification; informative sampling; Kernel; manifold learning; Manifolds; Measurement uncertainty; Principal component analysis; structure representative sampling; support vector machine; Support vector machines; Training; Uncertainty
• ISSN: 0196-2892; 1558-0644
• DOI: 10.1109/TGRS.2016.2591066

Active learning (AL) methods that select unlabeled samples only querying by informative measures (i.e., uncertainty and/or diversity criteria) have been extensively investigated. However, these methods usually do not exploit the manifold structure of the unlabeled data from the geometrical point of view, a choice that might lead to a sample bias and consequently undesirable performances. To control and possibly overcome such drawbacks, this paper explores AL methods based on joint informative and manifold structure representative sampling (JI-MSRS). In JI-MSRS, a portion of the unlabeled samples that are added at each iteration is selected according to the informative measures, whereas another portion is selected according to their capability to represent the data cluster structure. Four popular manifold learning methods, namely, principle component analysis (PCA), linear discriminant analysis, kernel PCA, and neighborhood preserving embedding, are used to model the data structure. Then, Delaunay triangulation nets are used to build a discrete approximation of the geometrical structure of the unlabeled data cloud in a low-dimensional space. To show the effectiveness of this novel sampling strategy, results on three real multi-/hyperspectral data sets are presented, adding a thorough comparison with other state-of-the-art AL techniques. In comparison to conventional AL heuristics, the proposed techniques are able to obtain competitive or even better classification accuracy values.