Self-Supervised Convolutional Neural Network via Spectral Attention Module for Hyperspectral Image Classification
- 11 January 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 19 (1545598X) , 1-5
Abstract
Hyperspectral image (HSI) classification is a hot topic in the field of remote sensing, and convolutional neural networks (CNNs) have shown good classification performance for their capabilities of feature extraction. However, traditional CNN-based methods require a lot of labeled data during their training process, while the acquisition of labeled samples is complicated and time-consuming. In addition, a key issue for HSI classification is how to effectively explore the correlation within the spectral dimension and emphasize important spectral bands. In this letter, an end-to-end framework named spectral attention-based self-supervised CNN (SASCNN) is put forward for HSI classification. At first, the SASCNN takes raw 3-D cubes as input data, and a spectral attention module (SAM) is used to adaptively optimize channel-wise characteristics by adjusting the importance among continuous spectral bands. Then, by flexibly adding multilayer concatenation to integrate shallow and abstract features, the designed encoder-decoder part can be used to learn discriminative features and reproduce the inputs in a self-supervised manner. Experiments over the Heihe and Houston datasets demonstrate the effectiveness of the proposed self-supervised learning method.Keywords
Funding Information
- National Natural Science Foundation of China (42071302)
- Innovation Program for Chongqing Overseas Returnees (cx2019144)
This publication has 23 references indexed in Scilit:
- Self-Supervised Feature Learning With CRF Embedding for Hyperspectral Image ClassificationIEEE Transactions on Geoscience and Remote Sensing, 2018
- Self-Supervised Low-Rank Representation (SSLRR) for Hyperspectral Image ClassificationIEEE Transactions on Geoscience and Remote Sensing, 2018
- Cloud removal for hyperspectral remotely sensed images based on hyperspectral information fusionInternational Journal of Remote Sensing, 2018
- Supervised Deep Feature Extraction for Hyperspectral Image ClassificationIEEE Transactions on Geoscience and Remote Sensing, 2017
- Hyperspectral Image Spectral-Spatial Feature Extraction via Tensor Principal Component AnalysisIEEE Geoscience and Remote Sensing Letters, 2017
- Deep Feature Extraction and Classification of Hyperspectral Images Based on Convolutional Neural NetworksIEEE Transactions on Geoscience and Remote Sensing, 2016
- Unsupervised Spectral–Spatial Feature Learning With Stacked Sparse Autoencoder for Hyperspectral Imagery ClassificationIEEE Geoscience and Remote Sensing Letters, 2015
- Deep Convolutional Neural Networks for Hyperspectral Image ClassificationJournal of Sensors, 2015
- Meta-Parameter Free Unsupervised Sparse Feature LearningIEEE Transactions on Pattern Analysis and Machine Intelligence, 2014
- Dynamic classifier selection using spectral-spatial information for hyperspectral image classificationJournal of Applied Remote Sensing, 2014