LiteDenseNet: A Lightweight Network for Hyperspectral Image Classification

Hyperspectral Image (HSI) classification based on deep learning has been an attractive area in recent years. However, as a kind of data-driven algorithm, deep learning method usually requires numerous computational resources and high-quality labelled dataset, while the cost of high-performance computing and data annotation is expensive. In this paper, to reduce dependence on massive calculation and labelled samples, we propose a lightweight network architecture (LiteDenseNet) based on DenseNet for Hyperspectral Image Classification. Inspired by GoogLeNet and PeleeNet, we design a 3D two-way dense layer to capture the local and global features of the input. As convolution is a computationally intensive operation, we introduce group convolution to decrease calculation cost and parameter size further. Thus, the number of parameters and the consumptions of calculation are observably less than contrapositive deep learning methods, which means LiteDenseNet owns simpler architecture and higher efficiency. A series of quantitative experiences on 6 widely used hyperspectral datasets show that the proposed LiteDenseNet obtains the state-of-the-art performance, even though when the absence of labelled samples is severe.

[1]  Ronald Kemker,et al.  Self-Taught Feature Learning for Hyperspectral Image Classification , 2017, IEEE Transactions on Geoscience and Remote Sensing.

[2]  Frank Hutter,et al.  SGDR: Stochastic Gradient Descent with Warm Restarts , 2016, ICLR.

[3]  Xiangyu Zhang,et al.  ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design , 2018, ECCV.

[4]  François Chollet,et al.  Xception: Deep Learning with Depthwise Separable Convolutions , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[5]  Glenn Healey,et al.  Hyperspectral Region Classification Using a Three-Dimensional Gabor Filterbank , 2010, IEEE Transactions on Geoscience and Remote Sensing.

[6]  Filiberto Pla,et al.  Capsule Networks for Hyperspectral Image Classification , 2019, IEEE Transactions on Geoscience and Remote Sensing.

[7]  Qian Du,et al.  A linear constrained distance-based discriminant analysis for hyperspectral image classification , 2001, Pattern Recognit..

[8]  Lin Huang,et al.  A Multiscale Deep Middle-level Feature Fusion Network for Hyperspectral Classification , 2019, Remote. Sens..

[9]  Zhiming Luo,et al.  Spectral–Spatial Residual Network for Hyperspectral Image Classification: A 3-D Deep Learning Framework , 2018, IEEE Transactions on Geoscience and Remote Sensing.

[10]  Yiwen Sun,et al.  Three-dimensional Gabor feature extraction for hyperspectral imagery classification using a memetic framework , 2015, Inf. Sci..

[11]  Tianci Liu,et al.  DAGN: A Real-Time UAV Remote Sensing Image Vehicle Detection Framework , 2020, IEEE Geoscience and Remote Sensing Letters.

[12]  Ming-Wei Chang,et al.  BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding , 2019, NAACL.

[13]  Shutao Li,et al.  Multiscale Superpixel-Based Sparse Representation for Hyperspectral Image Classification , 2017, Remote. Sens..

[14]  Yaolin Liu,et al.  Exploring the potential of airborne hyperspectral image for estimating topsoil organic carbon: Effects of fractional-order derivative and optimal band combination algorithm , 2020 .

[15]  Qingshan Liu,et al.  Cascaded Recurrent Neural Networks for Hyperspectral Image Classification , 2017, IEEE Transactions on Geoscience and Remote Sensing.

[16]  Jonathan Cheung-Wai Chan,et al.  Evaluation of random forest and adaboost tree-based ensemble classification and spectral band selection for ecotope mapping using airborne hyperspectral imagery , 2008 .

[17]  Xiaogang Wang,et al.  Deep Learning Face Attributes in the Wild , 2014, 2015 IEEE International Conference on Computer Vision (ICCV).

[18]  Bo Chen,et al.  MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications , 2017, ArXiv.

[19]  Xiuping Jia,et al.  Deep Feature Extraction and Classification of Hyperspectral Images Based on Convolutional Neural Networks , 2016, IEEE Transactions on Geoscience and Remote Sensing.

[20]  Mercedes Eugenia Paoletti,et al.  Visual Attention-Driven Hyperspectral Image Classification , 2019, IEEE Transactions on Geoscience and Remote Sensing.

[21]  Junwei Han,et al.  Learning Compact and Discriminative Stacked Autoencoder for Hyperspectral Image Classification , 2019, IEEE Transactions on Geoscience and Remote Sensing.

[22]  Yunsong Li,et al.  Structure Tensor and Guided Filtering-Based Algorithm for Hyperspectral Anomaly Detection , 2019, IEEE Transactions on Geoscience and Remote Sensing.

[23]  Siamak Khorram,et al.  Hierarchical maximum-likelihood classification for improved accuracies , 1997, IEEE Trans. Geosci. Remote. Sens..

[24]  Quoc V. Le,et al.  SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition , 2019, INTERSPEECH.

[25]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[26]  Mark Sandler,et al.  MobileNetV2: Inverted Residuals and Linear Bottlenecks , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[27]  Deyu Meng,et al.  Integration of 3-dimensional discrete wavelet transform and Markov random field for hyperspectral image classification , 2017, Neurocomputing.

[28]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[29]  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.

[30]  Deyu Meng,et al.  Hyperspectral Image Classification With Convolutional Neural Network and Active Learning , 2020, IEEE Transactions on Geoscience and Remote Sensing.

[31]  Jocelyn Chanussot,et al.  Superresolution Land Cover Mapping Based on Pixel-, Subpixel-, and Superpixel-Scale Spatial Dependence With Pansharpening Technique , 2019, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[32]  Forrest N. Iandola,et al.  SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <1MB model size , 2016, ArXiv.

[33]  Gang Wang,et al.  Deep Learning-Based Classification of Hyperspectral Data , 2014, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[34]  Yang Lu,et al.  Hyperspectral Image Classification Based on Three-Dimensional Scattering Wavelet Transform , 2015, IEEE Transactions on Geoscience and Remote Sensing.

[35]  Xiao Xiang Zhu,et al.  Deep Recurrent Neural Networks for Hyperspectral Image Classification , 2017, IEEE Transactions on Geoscience and Remote Sensing.

[36]  Qian Du,et al.  Self-Paced Joint Sparse Representation for the Classification of Hyperspectral Images , 2019, IEEE Transactions on Geoscience and Remote Sensing.

[37]  Kilian Q. Weinberger,et al.  Densely Connected Convolutional Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[38]  Guoqiang Wang,et al.  Non-point source pollution risks in a drinking water protection zone based on remote sensing data embedded within a nutrient budget model. , 2019, Water research.

[39]  Lin Zhu,et al.  Generative Adversarial Networks for Hyperspectral Image Classification , 2018, IEEE Transactions on Geoscience and Remote Sensing.

[40]  Jun Fu,et al.  Dual Attention Network for Scene Segmentation , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[41]  Jie Geng,et al.  Spectral–Spatial Classification of Hyperspectral Image Based on Deep Auto-Encoder , 2016, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[42]  Wenju Wang,et al.  A Fast Dense Spectral-Spatial Convolution Network Framework for Hyperspectral Images Classification , 2018, Remote. Sens..

[43]  Joydeep Ghosh,et al.  Investigation of the random forest framework for classification of hyperspectral data , 2005, IEEE Transactions on Geoscience and Remote Sensing.

[44]  Quoc V. Le,et al.  Searching for MobileNetV3 , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[45]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[46]  Lorenzo Bruzzone,et al.  Classification of hyperspectral remote sensing images with support vector machines , 2004, IEEE Transactions on Geoscience and Remote Sensing.

[47]  Hao Wu,et al.  Semi-Supervised Deep Learning Using Pseudo Labels for Hyperspectral Image Classification , 2018, IEEE Transactions on Image Processing.

[48]  Xiangyu Zhang,et al.  ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[49]  Yue Wu,et al.  Double-Branch Multi-Attention Mechanism Network for Hyperspectral Image Classification , 2019, Remote. Sens..

[50]  Xing Zhao,et al.  Spectral–Spatial Classification of Hyperspectral Data Based on Deep Belief Network , 2015, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[51]  Charles X. Ling,et al.  Pelee: A Real-Time Object Detection System on Mobile Devices , 2018, NeurIPS.

[52]  Andrew K. Skidmore,et al.  Spatially-explicit modelling with support of hyperspectral data can improve prediction of plant traits , 2019, Remote Sensing of Environment.

[53]  Yang Yang,et al.  Classification of Hyperspectral Image Based on Double-Branch Dual-Attention Mechanism Network , 2019, Remote. Sens..

[54]  Zexuan Zhu,et al.  Computational intelligence in optical remote sensing image processing , 2018, Appl. Soft Comput..

[55]  Heesung Kwon,et al.  Going Deeper With Contextual CNN for Hyperspectral Image Classification , 2016, IEEE Transactions on Image Processing.

[56]  Licheng Jiao,et al.  Recursive Autoencoders-Based Unsupervised Feature Learning for Hyperspectral Image Classification , 2017, IEEE Geoscience and Remote Sensing Letters.

[57]  In-So Kweon,et al.  CBAM: Convolutional Block Attention Module , 2018, ECCV.