Active-Learning-Incorporated Deep Transfer Learning for Hyperspectral Image Classification
- 12 November 2018
- journal article
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 11 (11) , 4048-4062
Abstract
A hyperspectral image (HSI) includes a vast quantity of samples, a large number of bands, and randomly occurring redundancy. Classifying such complex data is challenging, and its classification performance can be affected significantly by the amount of labeled training samples, as well as the quality, position, and others factors of these samples. Collecting such labeled training samples is labor and time consuming, motivating the idea of taking advantage of labeled samples from other pre-existing related images. Therefore, transfer learning, which can mitigate the semantic gap between existing and new HSIs, has drawn increasing research attention. However, existing transfer learning methods for HSIs (which mainly concentrate on how to overcome the divergence among images) may fail to carefully consider the contents to be transferred and thus limit their performances. In this paper, we present two novel ideas: 1) we, for the first time, introduce an active learning process to initialize the salient samples on the HSI data, which would be transferred later; and 2) we propose constructing and connecting higher level features for the source and target HSI data to further overcome the cross-domain disparity. Different from existing methods, the proposed framework requires no a priori knowledge on the target domain, and it works for both homogeneous and heterogeneous HSI data. Experimental results on three real-world HSIs support the effectiveness of the proposed method for HSI classification.Keywords
Funding Information
- Qatar National Research Fund
- National Priorities Research Program (7-684-1-127)
This publication has 31 references indexed in Scilit:
- Active Learning by Querying Informative and Representative ExamplesIEEE Transactions on Pattern Analysis and Machine Intelligence, 2014
- Clustering by fast search and find of density peaksScience, 2014
- Heterogeneous Domain Adaptation and Classification by Exploiting the Correlation SubspaceIEEE Transactions on Image Processing, 2014
- Batch mode active sampling based on marginal probability distribution matching2012
- Margin Based Active Learning2007
- Active learning via transductive experimental design2006
- Canonical Correlation Analysis: An Overview with Application to Learning MethodsNeural Computation, 2004
- Toward intelligent training of supervised image classifications: directing training data acquisition for SVM classificationRemote Sensing of Environment, 2004
- Committee-Based Sampling For Training Probabilistic Classifiers1995
- Heterogeneous Uncertainty Sampling for Supervised Learning1994