Semi-Supervised Ground-to-Aerial Adaptation with Heterogeneous Features Learning for Scene Classification
Open Access
- 10 May 2018
- journal article
- research article
- Published by MDPI AG in ISPRS International Journal of Geo-Information
- Vol. 7 (5) , 182
Abstract
Currently, huge quantities of remote sensing images (RSIs) are becoming available. Nevertheless, the scarcity of labeled samples hinders the semantic understanding of RSIs. Fortunately, many ground-level image datasets with detailed semantic annotations have been collected in the vision community. In this paper, we attempt to exploit the abundant labeled ground-level images to build discriminative models for overhead-view RSI classification. However, images from the ground-level and overhead view are represented by heterogeneous features with different distributions; how to effectively combine multiple features and reduce the mismatch of distributions are two key problems in this scene-model transfer task. Specifically, a semi-supervised manifold-regularized multiple-kernel-learning (SMRMKL) algorithm is proposed for solving these problems. We employ multiple kernels over several features to learn an optimal combined model automatically. Multi-kernel Maximum Mean Discrepancy (MK-MMD) is utilized to measure the data mismatch. To make use of unlabeled target samples, a manifold regularized semi-supervised learning process is incorporated into our framework. Extensive experimental results on both cross-view and aerial-to-satellite scene datasets demonstrate that: (1) SMRMKL has an appealing extension ability to effectively fuse different types of visual features; and (2) manifold regularization can improve the adaptation performance by utilizing unlabeled target samples.Keywords
Funding Information
- National Natural Science Foundation of China (61303186)
This publication has 45 references indexed in Scilit:
- Kernel-Based Domain-Invariant Feature Selection in Hyperspectral Images for Transfer LearningIEEE Transactions on Geoscience and Remote Sensing, 2015
- Transfer Sparse Subspace Analysis for Unsupervised Cross-View Scene Model AdaptationIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2015
- Transferring Deep Convolutional Neural Networks for the Scene Classification of High-Resolution Remote Sensing ImageryRemote Sensing, 2015
- Unsupervised Cross-View Semantic Transfer for Remote Sensing Image ClassificationIEEE Geoscience and Remote Sensing Letters, 2015
- Spectral alignment of multi-temporal cross-sensor images with automated kernel canonical correlation analysisISPRS Journal of Photogrammetry and Remote Sensing, 2015
- Domain Adaptation With Preservation of Manifold Geometry for Hyperspectral Image ClassificationIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2015
- Visual Domain Adaptation: A survey of recent advancesIEEE Signal Processing Magazine, 2015
- Classifying Compound Structures in Satellite Images: A Compressed Representation for Fast QueriesIEEE Transactions on Geoscience and Remote Sensing, 2014
- The SUN Attribute Database: Beyond Categories for Deeper Scene UnderstandingInternational Journal of Computer Vision, 2014
- LIBSVMACM Transactions on Intelligent Systems and Technology, 2011