scholarly journals Combining Spectral Unmixing and 3D/2D Dense Networks with Early-Exiting Strategy for Hyperspectral Image Classification

2020 ◽  
Vol 12 (5) ◽  
pp. 779 ◽  
Author(s):  
Bei Fang ◽  
Yunpeng Bai ◽  
Ying Li
Keyword(s):  
Deep Learning ◽  
Network Performance ◽  
Hyperspectral Image ◽  
Spectral Unmixing ◽  
Classification Methods ◽  
Dense Network ◽  
Training Samples ◽  
Mixed Pixels ◽  
Benchmark Datasets ◽  
Hard Samples

Recently, Hyperspectral Image (HSI) classification methods based on deep learning models have shown encouraging performance. However, the limited numbers of training samples, as well as the mixed pixels due to low spatial resolution, have become major obstacles for HSI classification. To tackle these problems, we propose a resource-efficient HSI classification framework which introduces adaptive spectral unmixing into a 3D/2D dense network with early-exiting strategy. More specifically, on one hand, our framework uses a cascade of intermediate classifiers throughout the 3D/2D dense network that is trained end-to-end. The proposed 3D/2D dense network that integrates 3D convolutions with 2D convolutions is more capable of handling spectral-spatial features, while containing fewer parameters compared with the conventional 3D convolutions, and further boosts the network performance with limited training samples. On another hand, considering the existence of mixed pixels in HSI data, the pixels in HSI classification are divided into hard samples and easy samples. With the early-exiting strategy in these intermediate classifiers, the average accuracy can be improved by reducing the amount of computation cost for easy samples, thus focusing on classifying hard samples. Furthermore, for hard samples, an adaptive spectral unmixing method is proposed as a complementary source of information for classification, which brings considerable benefits to the final performance. Experimental results on four HSI benchmark datasets demonstrate that the proposed method can achieve better performance than state-of-the-art deep learning-based methods and other traditional HSI classification methods.

scholarly journals Classification of Hyperspectral Image Based on Double-Branch Dual-Attention Mechanism Network

2020 ◽  
Vol 12 (3) ◽  
pp. 582 ◽  
Author(s):  
Rui Li ◽  
Shunyi Zheng ◽  
Chenxi Duan ◽  
Yang Yang ◽  
Xiqi Wang
Keyword(s):  
Deep Learning ◽  
Hyperspectral Image ◽  
State Of The Art ◽  
Attention Mechanism ◽  
Superior Performance ◽  
Feature Maps ◽  
Spatial Features ◽  
Training Samples ◽  
Series Of Experiments

In recent years, researchers have paid increasing attention on hyperspectral image (HSI) classification using deep learning methods. To improve the accuracy and reduce the training samples, we propose a double-branch dual-attention mechanism network (DBDA) for HSI classification in this paper. Two branches are designed in DBDA to capture plenty of spectral and spatial features contained in HSI. Furthermore, a channel attention block and a spatial attention block are applied to these two branches respectively, which enables DBDA to refine and optimize the extracted feature maps. A series of experiments on four hyperspectral datasets show that the proposed framework has superior performance to the state-of-the-art algorithm, especially when the training samples are signally lacking.

scholarly journals Spatial-Aware Network for Hyperspectral Image Classification

2021 ◽  
Vol 13 (16) ◽  
pp. 3232
Author(s):  
Yantao Wei ◽  
Yicong Zhou
Keyword(s):  
Deep Learning ◽  
Domain Knowledge ◽  
Hyperspectral Image ◽  
Main Idea ◽  
Small Sample ◽  
Hierarchical Architecture ◽  
Edge Preserving ◽  
Side Window ◽  
Training Samples ◽  
Small Sample Sizes

Deep learning is now receiving widespread attention in hyperspectral image (HSI) classification. However, due to the imbalance between a huge number of weights and limited training samples, many problems and difficulties have arisen from the use of deep learning methods in HSI classification. To handle this issue, an efficient deep learning-based HSI classification method, namely, spatial-aware network (SANet) has been proposed in this paper. The main idea of SANet is to exploit discriminative spectral-spatial features by incorporating prior domain knowledge into the deep architecture, where edge-preserving side window filters are used as the convolution kernels. Thus, SANet has a small number of parameters to optimize. This makes it fit for small sample sizes. Furthermore, SANet is able not only to aware local spatial structures using side window filtering framework, but also to learn discriminative features making use of the hierarchical architecture and limited label information. The experimental results on four widely used HSI data sets demonstrate that our proposed SANet significantly outperforms many state-of-the-art approaches when only a small number of training samples are available.

scholarly journals Multiscale Deep Spatial Feature Extraction Using Virtual RGB Image for Hyperspectral Imagery Classification

2020 ◽  
Vol 12 (2) ◽  
pp. 280 ◽  
Author(s):  
Liqin Liu ◽  
Zhenwei Shi ◽  
Bin Pan ◽  
Ning Zhang ◽  
Huanlin Luo ◽  
...  
Keyword(s):  
Feature Extraction ◽  
Deep Learning ◽  
Hyperspectral Image ◽  
Feature Fusion ◽  
Hyperspectral Data ◽  
Learning Technology ◽  
Learning Networks ◽  
Spatial Features ◽  
Training Samples ◽  
Rgb Image

In recent years, deep learning technology has been widely used in the field of hyperspectral image classification and achieved good performance. However, deep learning networks need a large amount of training samples, which conflicts with the limited labeled samples of hyperspectral images. Traditional deep networks usually construct each pixel as a subject, ignoring the integrity of the hyperspectral data and the methods based on feature extraction are likely to lose the edge information which plays a crucial role in the pixel-level classification. To overcome the limit of annotation samples, we propose a new three-channel image build method (virtual RGB image) by which the trained networks on natural images are used to extract the spatial features. Through the trained network, the hyperspectral data are disposed as a whole. Meanwhile, we propose a multiscale feature fusion method to combine both the detailed and semantic characteristics, thus promoting the accuracy of classification. Experiments show that the proposed method can achieve ideal results better than the state-of-art methods. In addition, the virtual RGB image can be extended to other hyperspectral processing methods that need to use three-channel images.

scholarly journals Hyperspectral Image Classification Based on Parameter-Optimized 3D-CNNs Combined with Transfer Learning and Virtual Samples

2018 ◽  
Vol 10 (9) ◽  
pp. 1425 ◽  
Author(s):  
Xuefeng Liu ◽  
Qiaoqiao Sun ◽  
Yue Meng ◽  
Min Fu ◽  
Salah Bourennane
Keyword(s):  
Transfer Learning ◽  
Network Performance ◽  
Hyperspectral Image ◽  
Three Dimensional ◽  
Feature Space ◽  
Training Samples ◽  
Virtual Samples ◽  
3D Cnn ◽  
Target Data

Recent research has shown that spatial-spectral information can help to improve the classification of hyperspectral images (HSIs). Therefore, three-dimensional convolutional neural networks (3D-CNNs) have been applied to HSI classification. However, a lack of HSI training samples restricts the performance of 3D-CNNs. To solve this problem and improve the classification, an improved method based on 3D-CNNs combined with parameter optimization, transfer learning, and virtual samples is proposed in this paper. Firstly, to optimize the network performance, the parameters of the 3D-CNN of the HSI to be classified (target data) are adjusted according to the single variable principle. Secondly, in order to relieve the problem caused by insufficient samples, the weights in the bottom layers of the parameter-optimized 3D-CNN of the target data can be transferred from another well trained 3D-CNN by a HSI (source data) with enough samples and the same feature space as the target data. Then, some virtual samples can be generated from the original samples of the target data to further alleviate the lack of HSI training samples. Finally, the parameter-optimized 3D-CNN with transfer learning can be trained by the training samples consisting of the virtual and the original samples. Experimental results on real-world hyperspectral satellite images have shown that the proposed method has great potential prospects in HSI classification.

scholarly journals Deep Learning Network Intensification for Preventing Noisy-Labeled Samples for Remote Sensing Classification

2021 ◽  
Vol 13 (9) ◽  
pp. 1689
Author(s):  
Chuang Lin ◽  
Shanxin Guo ◽  
Jinsong Chen ◽  
Luyi Sun ◽  
Xiaorou Zheng ◽  
...  
Keyword(s):  
Remote Sensing ◽  
Deep Learning ◽  
Network Performance ◽  
Aerial Image ◽  
Label Noise ◽  
Remote Sensing Classification ◽  
Learning Network ◽  
Training Samples ◽  
Deep Learning Network ◽  
The Impact

The deep-learning-network performance depends on the accuracy of the training samples. The training samples are commonly labeled by human visual investigation or inherited from historical land-cover or land-use maps, which usually contain label noise, depending on subjective knowledge and the time of the historical map. Helping the network to distinguish noisy labels during the training process is a prerequisite for applying the model for training across time and locations. This study proposes an antinoise framework, the Weight Loss Network (WLN), to achieve this goal. The WLN contains three main parts: (1) the segmentation subnetwork, which any state-of-the-art segmentation network can replace; (2) the attention subnetwork (λ); and (3) the class-balance coefficient (α). Four types of label noise (an insufficient label, redundant label, missing label and incorrect label) were simulated by dilate and erode processing to test the network’s antinoise ability. The segmentation task was set to extract buildings from the Inria Aerial Image Labeling Dataset, which includes Austin, Chicago, Kitsap County, Western Tyrol and Vienna. The network’s performance was evaluated by comparing it with the original U-Net model by adding noisy training samples with different noise rates and noise levels. The result shows that the proposed antinoise framework (WLN) can maintain high accuracy, while the accuracy of the U-Net model dropped. Specifically, after adding 50% of dilated-label samples at noise level 3, the U-Net model’s accuracy dropped by 12.7% for OA, 20.7% for the Mean Intersection over Union (MIOU) and 13.8% for Kappa scores. By contrast, the accuracy of the WLN dropped by 0.2% for OA, 0.3% for the MIOU and 0.8% for Kappa scores. For eroded-label samples at the same level, the accuracy of the U-Net model dropped by 8.4% for OA, 24.2% for the MIOU and 43.3% for Kappa scores, while the accuracy of the WLN dropped by 4.5% for OA, 4.7% for the MIOU and 0.5% for Kappa scores. This result shows that the antinoise framework proposed in this paper can help current segmentation models to avoid the impact of noisy training labels and has the potential to be trained by a larger remote sensing image set regardless of the inner label error.

scholarly journals Deep-learning jets with uncertainties and more

2020 ◽  
Vol 8 (1) ◽  
Author(s):  
Sven Bollweg ◽  
Manuel Haussmann ◽  
Gregor Kasieczka ◽  
Michel Luchmann ◽  
Tilman Plehn ◽  
...  
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Bayesian Networks ◽  
Network Performance ◽  
Energy Scale ◽  
Error Band ◽  
Training Samples ◽  
Pile Up ◽  
Stability Issues ◽  
And Control

Bayesian neural networks allow us to keep track of uncertainties, for example in top tagging, by learning a tagger output together with an error band. We illustrate the main features of Bayesian versions of established deep-learning taggers. We show how they capture statistical uncertainties from finite training samples, systematics related to the jet energy scale, and stability issues through pile-up. Altogether, Bayesian networks offer many new handles to understand and control deep learning at the LHC without introducing a visible prior effect and without compromising the network performance.

scholarly journals Hyperspectral Image Classification Based on Two-Branch Spectral–Spatial-Feature Attention Network

2021 ◽  
Vol 13 (21) ◽  
pp. 4262
Author(s):  
Hanjie Wu ◽  
Dan Li ◽  
Yujian Wang ◽  
Xiaojun Li ◽  
Fanqiang Kong ◽  
...  
Keyword(s):  
Hyperspectral Image ◽  
Classification Performance ◽  
Hybrid Architecture ◽  
Classification Methods ◽  
Attention Network ◽  
Spatial Feature ◽  
Spatial Features ◽  
Original Dataset ◽  
Training Samples ◽  
Feature Attention

Although most of deep-learning-based hyperspectral image (HSI) classification methods achieve great performance, there still remains a challenge to utilize small-size training samples to remarkably enhance the classification accuracy. To tackle this challenge, a novel two-branch spectral–spatial-feature attention network (TSSFAN) for HSI classification is proposed in this paper. Firstly, two inputs with different spectral dimensions and spatial sizes are constructed, which can not only reduce the redundancy of the original dataset but also accurately explore the spectral and spatial features. Then, we design two parallel 3DCNN branches with attention modules, in which one focuses on extracting spectral features and adaptively learning the more discriminative spectral channels, and the other focuses on exploring spatial features and adaptively learning the more discriminative spatial structures. Next, the feature attention module is constructed to automatically adjust the weights of different features based on their contributions for classification to remarkably improve the classification performance. Finally, we design the hybrid architecture of 3D–2DCNN to acquire the final classification result, which can significantly decrease the sophistication of the network. Experimental results on three HSI datasets indicate that our presented TSSFAN method outperforms several of the most advanced classification methods.

scholarly journals Hyperspectral Image Classification with Capsule Network Using Limited Training Samples

Sensors ◽  
2018 ◽  
Vol 18 (9) ◽  
pp. 3153 ◽  
Author(s):  
Fei Deng ◽  
Shengliang Pu ◽  
Xuehong Chen ◽  
Yusheng Shi ◽  
Ting Yuan ◽  
...  
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Network Architecture ◽  
Hyperspectral Image ◽  
Machine Learning Algorithms ◽  
Superior Performance ◽  
Support Vector ◽  
Complex Data ◽  
Training Samples ◽  
Limited Training Samples

Deep learning techniques have boosted the performance of hyperspectral image (HSI) classification. In particular, convolutional neural networks (CNNs) have shown superior performance to that of the conventional machine learning algorithms. Recently, a novel type of neural networks called capsule networks (CapsNets) was presented to improve the most advanced CNNs. In this paper, we present a modified two-layer CapsNet with limited training samples for HSI classification, which is inspired by the comparability and simplicity of the shallower deep learning models. The presented CapsNet is trained using two real HSI datasets, i.e., the PaviaU (PU) and SalinasA datasets, representing complex and simple datasets, respectively, and which are used to investigate the robustness or representation of every model or classifier. In addition, a comparable paradigm of network architecture design has been proposed for the comparison of CNN and CapsNet. Experiments demonstrate that CapsNet shows better accuracy and convergence behavior for the complex data than the state-of-the-art CNN. For CapsNet using the PU dataset, the Kappa coefficient, overall accuracy, and average accuracy are 0.9456, 95.90%, and 96.27%, respectively, compared to the corresponding values yielded by CNN of 0.9345, 95.11%, and 95.63%. Moreover, we observed that CapsNet has much higher confidence for the predicted probabilities. Subsequently, this finding was analyzed and discussed with probability maps and uncertainty analysis. In terms of the existing literature, CapsNet provides promising results and explicit merits in comparison with CNN and two baseline classifiers, i.e., random forests (RFs) and support vector machines (SVMs).

scholarly journals Wide Sliding Window and Subsampling Network for Hyperspectral Image Classification

2021 ◽  
Vol 13 (7) ◽  
pp. 1290
Author(s):  
Jiangbo Xi ◽  
Okan K. Ersoy ◽  
Jianwu Fang ◽  
Ming Cong ◽  
Tianjun Wu ◽  
...  
Keyword(s):  
Deep Learning ◽  
High Performance ◽  
Large Scale ◽  
Hyperspectral Image ◽  
Sliding Window ◽  
Spectral Features ◽  
Learning Methods ◽  
Training Time ◽  
Sliding Windows ◽  
Training Samples

Recently, deep learning methods, for example, convolutional neural networks (CNNs), have achieved high performance in hyperspectral image (HSI) classification. The limited training samples of HSI images make it hard to use deep learning methods with many layers and a large number of convolutional kernels as in large scale imagery tasks, and CNN-based methods usually need long training time. In this paper, we present a wide sliding window and subsampling network (WSWS Net) for HSI classification. It is based on layers of transform kernels with sliding windows and subsampling (WSWS). It can be extended in the wide direction to learn both spatial and spectral features more efficiently. The learned features are subsampled to reduce computational loads and to reduce memorization. Thus, layers of WSWS can learn higher level spatial and spectral features efficiently, and the proposed network can be trained easily by only computing linear weights with least squares. The experimental results show that the WSWS Net achieves excellent performance with different hyperspectral remotes sensing datasets compared with other shallow and deep learning methods. The effects of ratio of training samples, the sizes of image patches, and the visualization of features in WSWS layers are presented.

Sign in / Sign up

Export Citation Format

Share Document