Learning and Transferring Deep Joint Spectral–Spatial Features for Hyperspectral Classification
Top Cited Papers
- 16 May 2017
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 55 (8), 4729-4742
- https://doi.org/10.1109/tgrs.2017.2698503
Abstract
Feature extraction is of significance for hyperspectral image (HSI) classification. Compared with conventional hand-crafted feature extraction, deep learning can automatically learn features with discriminative information. However, two issues exist in applying deep learning to HSIs. One issue is how to jointly extract spectral features and spatial features, and the other one is how to train the deep model when training samples are scarce. In this paper, a deep convolutional neural network with two-branch architecture is proposed to extract the joint spectral-spatial features from HSIs. The two branches of the proposed network are devoted to features from the spectral domain as well as the spatial domain. The learned spectral features and spatial features are then concatenated and fed to fully connected layers to extract the joint spectral-spatial features for classification. When the training samples are limited, we investigate the transfer learning to improve the performance. Low and mid-layers of the network are pretrained and transferred from other data sources; only top layers are trained with limited training samples extracted from the target scene. Experiments on Airborne Visible/Infrared Imaging Spectrometer and Reflective Optics System Imaging Spectrometer data demonstrate that the learned deep joint spectral-spatial features are discriminative, and competitive classification results can be achieved when compared with state-of-the-art methods. The experiments also reveal that the transferred features boost the classification performance.Keywords
Funding Information
- National Natural Science Foundation of China (61371152, 61071172, 61374162)
- National Natural Science Foundation of China
- South Korean National Research Foundation Joint Funded Cooperation Program (61511140292)
- New Century Excellent Talents Award Program from the Ministry of Education of China (NCET-12-0464)
- Ministry of Education Scientific Research Foundation for the Returned Overseas
- Fundamental Research Funds for the Central Universities (3102015ZY045)
- China Scholarship Council for joint Ph.D. students (201506290120)
- Innovation Foundation of Doctor Dissertation of Northwestern Polytechnical University (CX201621)
This publication has 43 references indexed in Scilit:
- Multiple Feature Learning for Hyperspectral Image ClassificationIEEE Transactions on Geoscience and Remote Sensing, 2014
- Gabor Feature-Based Collaborative Representation for Hyperspectral Imagery ClassificationIEEE Transactions on Geoscience and Remote Sensing, 2014
- Transfer Learning for Visual Categorization: A SurveyIEEE Transactions on Neural Networks and Learning Systems, 2014
- Deep Learning-Based Classification of Hyperspectral DataIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2014
- Biodiversity Mapping in a Tropical West African Forest with Airborne Hyperspectral DataPLOS ONE, 2014
- Hyperspectral Image Denoising via Sparse Representation and Low-Rank ConstraintIEEE Transactions on Geoscience and Remote Sensing, 2014
- Stochastic Gradient Descent TricksLecture Notes in Computer Science, 2012
- LIBSVMACM Transactions on Intelligent Systems and Technology, 2011
- Reducing the Dimensionality of Data with Neural NetworksScience, 2006
- Thematic Map ComparisonPhotogrammetric Engineering & Remote Sensing, 2004