Journal Article10.1109/LGRS.2019.2945848
Hyperspectral Image Classification With Data Augmentation and Classifier Fusion
27
TL;DR: Since both data augmentation and classifier fusion are effective to deal with limited samples, the proposed method shows superior performance in the classification of HSIs, which can be demonstrated by the experimental results on two benchmark HSI data sets.
read more
Abstract: Recently, deep convolutional neural network (DCNN)-based methods have achieved much success in hyperspectral image (HSI) classification, when sufficient labeled samples are provided during training. However, due to the expensive cost of labeling in HSIs, only limited labeled samples can be given in practice, which often causes these methods to be overfitting. To address this problem, we present a new HSI classification method in this study, which is constructed in the following two steps. First, we establish a data mixture model to augment the labeled training set quadratically and train a DCNN-based classifier on it. Then, through randomly sampling the coefficient in the data mixture model, we obtain several independent classifiers and fuse them with a voting strategy to produce the final classification results. Since both data augmentation and classifier fusion are effective to deal with limited samples, the proposed method shows superior performance in the classification of HSIs, which can be demonstrated by the experimental results on two benchmark HSI data sets.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Hyperspectral image classification on insufficient-sample and feature learning using deep neural networks: A review
Naftaly Wambugu,Yiping Chen,Zhenlong Xiao,Kun Tan,Mingqiang Wei,Xiaoxue Liu,Jonathan Li,Jonathan Li +7 more
TL;DR: In this paper, a review of the current methods that handle labeled data insufficiency and the current feature learning methods for hyperspectral image classification using deep convolution neural networks (DCCNs) is presented.
94
Deep Residual Involution Network for Hyperspectral Image Classification
TL;DR: This article combines a novel operation called involution with residual learning and develops a new deep residual involution network (DRIN) for HSI classification, which achieves better classification results when compared with both traditional machine learning-based and convolution-based methods on four HSI datasets.
28
Spectral–Spatial Graph Attention Network for Semisupervised Hyperspectral Image Classification
TL;DR: In this paper , a spectral-spatial graph attention network (SSGAT) is proposed for hyperspectral image classification, which takes all samples (training and testing samples) as nodes and establishes an edge set among them to form a graph structure.
21
Graph Meta Transfer Network for Heterogeneous Few-Shot Hyperspectral Image Classification
TL;DR: Zhang et al. as discussed by the authors proposed a novel heterogeneous few-shot learning (FSL) method, namely graph meta transfer network (GMTN), which integrated graph sample and aggregate network (GraphSAGE) and meta-learning, which are both inductive learning, into a unified framework.
21
References
•Proceedings Article
mixup: Beyond Empirical Risk Minimization
Hongyi Zhang,Moustapha Cisse,Yann N. Dauphin,David Lopez-Paz +3 more
- 25 Oct 2017
TL;DR: This work proposes mixup, a simple learning principle that trains a neural network on convex combinations of pairs of examples and their labels, which improves the generalization of state-of-the-art neural network architectures.
•Posted Content
mixup: Beyond Empirical Risk Minimization
TL;DR: Mixup as discussed by the authors trains a neural network on convex combinations of pairs of examples and their labels, and regularizes the neural network to favor simple linear behavior in between training examples, which improves the generalization of state-of-the-art neural network architectures.
4.2K
Deep Convolutional Neural Networks for Hyperspectral Image Classification
TL;DR: Experimental results based on several hyperspectral image data sets demonstrate that the proposed method can achieve better classification performance than some traditional methods, such as support vector machines and the conventional deep learning-based methods.
Hyperspectral Image Classification Using Deep Pixel-Pair Features
TL;DR: Experimental results based on several hyperspectral image data sets demonstrate that the proposed pixel-pair method can achieve better classification performance than the conventional deep learning-based method.
854
Recent Advances on Spectral–Spatial Hyperspectral Image Classification: An Overview and New Guidelines
TL;DR: A concept of spatial dependency system that involves pixel dependency and label dependency, with two main factors: neighborhood covering and neighborhood importance is developed, and several representative spectral–spatial classification methods are applied on real-world hyperspectral data.
645