Band Selection from Hyperspectral Images Using Attention-based Convolutional Neural Networks

This paper introduces new attention-based convolutional neural networks for selecting bands from hyperspectral images. The proposed approach re-uses convolutional activations at different depths, identifying the most informative regions of the spectrum with the help of gating mechanisms. Our attention techniques are modular and easy to implement, and they can be seamlessly trained end-to-end using gradient descent. Our rigorous experiments showed that deep models equipped with the attention mechanism deliver high-quality classification, and repeatedly identify significant bands in the training data, permitting the creation of refined and extremely compact sets that retain the most meaningful features.

[1]  David A. Clausi,et al.  ST-IRGS: A Region-Based Self-Training Algorithm Applied to Hyperspectral Image Classification and Segmentation , 2018, IEEE Transactions on Geoscience and Remote Sensing.

[2]  Jakub Nalepa,et al.  Validating Hyperspectral Image Segmentation , 2018, IEEE Geoscience and Remote Sensing Letters.

[3]  Licheng Jiao,et al.  Hyperspectral Band Selection Using Improved Classification Map , 2017, IEEE Geoscience and Remote Sensing Letters.

[4]  Lukasz Kaiser,et al.  Attention is All you Need , 2017, NIPS.

[5]  Kerstin Paech,et al.  Anomaly detection for machine learning redshifts applied to SDSS galaxies , 2015, 1503.08214.

[6]  Tao Mei,et al.  Look Closer to See Better: Recurrent Attention Convolutional Neural Network for Fine-Grained Image Recognition , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[7]  Zhiwei Ye,et al.  A band selection method for airborne hyperspectral image based on chaotic binary coded gravitational search algorithm , 2018, Neurocomputing.

[8]  Qian Du,et al.  Unsupervised Hyperspectral Band Selection Using Graphics Processing Units , 2011, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[9]  Adolfo Martínez Usó,et al.  Clustering-Based Hyperspectral Band Selection Using Information Measures , 2007, IEEE Transactions on Geoscience and Remote Sensing.

[10]  P. Rousseeuw,et al.  A fast algorithm for the minimum covariance determinant estimator , 1999 .

[11]  Yuxin Peng,et al.  The application of two-level attention models in deep convolutional neural network for fine-grained image classification , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[12]  Daizhi Liu,et al.  Recursive spectral similarity measure-based band selection for anomaly detection in hyperspectral imagery , 2010 .

[13]  Fei Li,et al.  Unsupervised Band Selection of Hyperspectral Images via Multi-Dictionary Sparse Representation , 2018, IEEE Access.

[14]  Maoguo Gong,et al.  Unsupervised Band Selection Based on Evolutionary Multiobjective Optimization for Hyperspectral Images , 2016, IEEE Transactions on Geoscience and Remote Sensing.

[15]  Jianbin Qiu,et al.  A novel approach to hyperspectral band selection based on spectral shape similarity analysis and fast branch and bound search , 2014, Eng. Appl. Artif. Intell..

[16]  Lei Ma,et al.  A Novel Wrapper Approach for Feature Selection in Object-Based Image Classification Using Polygon-Based Cross-Validation , 2017, IEEE Geoscience and Remote Sensing Letters.

[17]  Licheng Jiao,et al.  Hyperspectral band selection with objective image quality assessment , 2017 .

[18]  Junjun Jiang,et al.  Spectral-Spatial Feature Extraction of Hyperspectral Images Based on Propagation Filter , 2018, Sensors.

[19]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[20]  Hao Wu,et al.  A Hybrid Evolutionary Approach to Band Selection for Hyperspectral Image Classification , 2010 .

[21]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[22]  Maoguo Gong,et al.  Hyperspectral band selection based on multi-objective optimization with high information and low redundancy , 2018, Appl. Soft Comput..

[23]  Hai Wan,et al.  Representative band selection for hyperspectral image classification , 2017, J. Vis. Commun. Image Represent..

[24]  Shutao Li,et al.  Learning to Diversify Deep Belief Networks for Hyperspectral Image Classification , 2017, IEEE Transactions on Geoscience and Remote Sensing.

[25]  Bo Zhao,et al.  Diversified Visual Attention Networks for Fine-Grained Object Classification , 2016, IEEE Transactions on Multimedia.

[26]  Robert I. Damper,et al.  Band Selection for Hyperspectral Image Classification Using Mutual Information , 2006, IEEE Geoscience and Remote Sensing Letters.

[27]  Licheng Jiao,et al.  Supervised Band Selection Using Local Spatial Information for Hyperspectral Image , 2016, IEEE Geoscience and Remote Sensing Letters.

[28]  Pau Rodríguez,et al.  A Painless Attention Mechanism for Convolutional Neural Networks , 2018 .

[29]  Qian Du,et al.  A joint band prioritization and band-decorrelation approach to band selection for hyperspectral image classification , 1999, IEEE Trans. Geosci. Remote. Sens..

[30]  Paramartha Dutta,et al.  A Hybrid Approach for Band Selection of Hyperspectral Images , 2017 .

[31]  Xiuping Jia,et al.  Hyperspectral Image Classification Using Convolutional Neural Networks and Multiple Feature Learning , 2018, Remote. Sens..

[32]  Taner Ince,et al.  Sparse Representation-Based Hyperspectral Image Classification Using Multiscale Superpixels and Guided Filter , 2019, IEEE Geoscience and Remote Sensing Letters.

[33]  Shihong Du,et al.  Spectral–Spatial Feature Extraction for Hyperspectral Image Classification: A Dimension Reduction and Deep Learning Approach , 2016, IEEE Transactions on Geoscience and Remote Sensing.

[34]  Xiao Liu,et al.  Fully Convolutional Attention Localization Networks: Efficient Attention Localization for Fine-Grained Recognition , 2016, ArXiv.

[35]  Dan Hu,et al.  Hyperspectral Band Selection Based on Deep Convolutional Neural Network and Distance Density , 2017, IEEE Geoscience and Remote Sensing Letters.