Semisupervised Transfer Component Analysis for Domain Adaptation in Remote Sensing Image Classification

• Published in: IEEE transactions on geoscience and remote sensing Vol. 53; no. 7; pp. 3550 - 3564
• Main Authors: Matasci, Giona, Volpi, Michele, Kanevski, Mikhail, Bruzzone, Lorenzo, Tuia, Devis
• Format: Journal Article
• Language: English
• Published: IEEE 01.07.2015
• Subjects: Domain adaptation (DA); Feature extraction; Iron; Kernel; kernel methods; land-cover classification; Manifolds; maximum mean discrepancy (MMD); model portability; radiometric normalization; Radiometry; Remote sensing; semisupervised transfer component analysis (TCA); Training; Domain adaptation (DA); kernel methods; semisupervised transfer component analysis (TCA); radiometric normalization; land-cover classification; maximum mean discrepancy (MMD); model portability

In this paper, we study the problem of feature extraction for knowledge transfer between multiple remotely sensed images in the context of land-cover classification. Several factors such as illumination, atmospheric, and ground conditions cause radiometric differences between images of similar scene...