Hyperspectral Classification Based on Lightweight 3-D-CNN With Transfer Learning

Abstract

Recently, hyperspectral image (HSI) classification approaches based on deep learning (DL) models have been proposed and shown promising performance. However, because of very limited available training samples and massive model parameters, DL methods may suffer from overfitting. In this paper, we propose an end-to-end 3-D lightweight convolutional neural network (CNN) (abbreviated as 3-D-LWNet) for limited samples-based HSI classification. Compared with conventional 3-D-CNN models, the proposed 3-D-LWNet has a deeper network structure, less parameters, and lower computation cost, resulting in better classification performance. To further alleviate the small sample problem, we also propose two transfer learning strategies: 1) cross-sensor strategy, in which we pretrain a 3-D model in the source HSI data sets containing a greater number of labeled samples and then transfer it to the target HSI data sets and 2) cross-modal strategy, in which we pretrain a 3-D model in the 2-D RGB image data sets containing a large number of samples and then transfer it to the target HSI data sets. In contrast to previous approaches, we do not impose restrictions over the source data sets, in which they do not have to be collected by the same sensors as the target data sets. Experiments on three public HSI data sets captured by different sensors demonstrate that our model achieves competitive performance for HSI classification compared to several state-of-the-art methods

16 pages. Accepted to IEEE Trans. Geosci. Remote Sens. Code is available at: https://github.com/hkzhang91/LWNet

References in corpus (7)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• SSD: Single Shot MultiBox Detector
• MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
• MobileNetV2: Inverted Residuals and Linear Bottlenecks
• Hydrothermal formation of Clay-Carbonate alteration assemblages in the Nili Fossae region of Mars
• Spectral Curve Fitting for Automatic Hyperspectral Data Analysis
• The MARTE VNIR Imaging Spectrometer Experiment: Design and Analysis

Cited by in corpus (12)

• Hyperspectral Image Classification-Traditional to Deep Models: A Survey for Future Prospects
• A Survey: Deep Learning for Hyperspectral Image Classification with Few Labeled Samples
• A Spectral-Spatial-Dependent Global Learning Framework for Insufficient and Imbalanced Hyperspectral Image Classification
• Adaptive DropBlock Enhanced Generative Adversarial Networks for Hyperspectral Image Classification
• A Comprehensive Survey for Hyperspectral Image Classification: The Evolution from Conventional to Transformers and Mamba Models
• S${}^2$Mamba: A Spatial-spectral State Space Model for Hyperspectral Image Classification
• 3D-ANAS: 3D Asymmetric Neural Architecture Search for Fast Hyperspectral Image Classification
• Physically-Constrained Transfer Learning through Shared Abundance Space for Hyperspectral Image Classification
• Grafting Transformer on Automatically Designed Convolutional Neural Network for Hyperspectral Image Classification
• Exploring Cross-Domain Pretrained Model for Hyperspectral Image Classification
• Active Deep Densely Connected Convolutional Network for Hyperspectral Image Classification
• A Convolutional Neural Network with Parallel Multi-Scale Spatial Pooling to Detect Temporal Changes in SAR Images