MSSL: Hyperspectral and Panchromatic Images Fusion via Multiresolution Spatial-Spectral Feature Learning Networks

2021 ◽  
pp. 1-13
Author(s):  
Jiahui Qu ◽  
Yanzi Shi ◽  
Weiying Xie ◽  
Yunsong Li ◽  
Xianyun Wu ◽  
...  
Keyword(s):  
Spectral Feature ◽  
Feature Learning ◽  
Learning Networks

scholarly journals Three-Dimensional ResNeXt Network Using Feature Fusion and Label Smoothing for Hyperspectral Image Classification

Sensors ◽  
2020 ◽  
Vol 20 (6) ◽  
pp. 1652 ◽  
Author(s):  
Peida Wu ◽  
Ziguan Cui ◽  
Zongliang Gan ◽  
Feng Liu
Keyword(s):  
Hyperspectral Image ◽  
Feature Fusion ◽  
Three Dimensional ◽  
Spectral Feature ◽  
Feature Learning ◽  
Hyperspectral Image Classification ◽  
Training Samples ◽  
Dramatic Rise ◽  
Classification Tasks ◽  
The One

In recent years, deep learning methods have been widely used in the hyperspectral image (HSI) classification tasks. Among them, spectral-spatial combined methods based on the three-dimensional (3-D) convolution have shown good performance. However, because of the three-dimensional convolution, increasing network depth will result in a dramatic rise in the number of parameters. In addition, the previous methods do not make full use of spectral information. They mostly use the data after dimensionality reduction directly as the input of networks, which result in poor classification ability in some categories with small numbers of samples. To address the above two issues, in this paper, we designed an end-to-end 3D-ResNeXt network which adopts feature fusion and label smoothing strategy further. On the one hand, the residual connections and split-transform-merge strategy can alleviate the declining-accuracy phenomenon and decrease the number of parameters. We can adjust the hyperparameter cardinality instead of the network depth to extract more discriminative features of HSIs and improve the classification accuracy. On the other hand, in order to improve the classification accuracies of classes with small numbers of samples, we enrich the input of the 3D-ResNeXt spectral-spatial feature learning network by additional spectral feature learning, and finally use a loss function modified by label smoothing strategy to solve the imbalance of classes. The experimental results on three popular HSI datasets demonstrate the superiority of our proposed network and an effective improvement in the accuracies especially for the classes with small numbers of training samples.

scholarly journals Image Classification in HTP Test Based on Convolutional Neural Network Model

2021 ◽  
Vol 2021 ◽  
pp. 1-8
Author(s):  
Lin Liu
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Image Classification ◽  
Reliability And Validity ◽  
Feature Learning ◽  
Human Vision ◽  
Assessment Process ◽  
Learning Networks ◽  
Good Reliability

HTP test in psychometrics is a widely studied and applied psychological assessment technique. HTP test is a kind of projection test, which refers to the free expression of painting itself and its creativity. Therefore, the form of group psychological counselling is widely used in mental health education. Compared with traditional neural networks, deep learning networks have deeper and more network layers and can learn more complex processing functions. In this stage, image recognition technology can be used as an assistant of human vision. People can quickly get the information in the picture through retrieval. For example, you can take a picture of an object that is difficult to describe and quickly search the content related to it. Convolutional neural network, which is widely used in the image classification task of computer vision, can automatically complete feature learning on the data without manual feature extraction. Compared with the traditional test, the test can reflect the painting characteristics of different groups. After quantitative scoring, it has good reliability and validity. It has high application value in psychological evaluation, especially in the diagnosis of mental diseases. This paper focuses on the subjectivity of HTP evaluation. Convolutional neural network is a mature technology in deep learning. The traditional HTP assessment process relies on the experience of researchers to extract painting features and classification.

scholarly journals Semi-Supervised Deep Metric Learning Networks for Classification of Polarimetric SAR Data

2020 ◽  
Vol 12 (10) ◽  
pp. 1593
Author(s):  
Hongying Liu ◽  
Ruyi Luo ◽  
Fanhua Shang ◽  
Xuechun Meng ◽  
Shuiping Gou ◽  
...  
Keyword(s):  
Real World ◽  
Metric Learning ◽  
Feature Learning ◽  
Linear Mapping ◽  
Layer By Layer ◽  
Learning Networks ◽  
Distance Metric ◽  
Linear Projection ◽  
Deep Metric Learning

Recently, classification methods based on deep learning have attained sound results for the classification of Polarimetric synthetic aperture radar (PolSAR) data. However, they generally require a great deal of labeled data to train their models, which limits their potential real-world applications. This paper proposes a novel semi-supervised deep metric learning network (SSDMLN) for feature learning and classification of PolSAR data. Inspired by distance metric learning, we construct a network, which transforms the linear mapping of metric learning into the non-linear projection in the layer-by-layer learning. With the prior knowledge of the sample categories, the network also learns a distance metric under which all pairs of similarly labeled samples are closer and dissimilar samples have larger relative distances. Moreover, we introduce a new manifold regularization to reduce the distance between neighboring samples since they are more likely to be homogeneous. The categorizing is achieved by using a simple classifier. Several experiments on both synthetic and real-world PolSAR data from different sensors are conducted and they demonstrate the effectiveness of SSDMLN with limited labeled samples, and SSDMLN is superior to state-of-the-art methods.

scholarly journals ATTENTION BASED CONVOLUTIONAL NEURAL NETWORK FOR BUILDING EXTRACTION FROM VERY HIGH RESOLUTION REMOTE SENSING IMAGE

2019 ◽  
Vol XLII-4/W18 ◽  
pp. 507-512
Author(s):  
H. R. Hosseinpoor ◽  
F. Samadzadegan
Keyword(s):  
Remote Sensing ◽  
High Resolution ◽  
Feature Learning ◽  
Remote Sensing Data ◽  
Superior Performance ◽  
Model Complexity ◽  
Building Extraction ◽  
Learning Networks ◽  
Benchmark Datasets ◽  
Very High

Abstract. Buildings are a major element in the formation of cities and are essential for urban mapping. The precise extraction of buildings from remote sensing data has become a significant topic and has received much attention in recent years. The recently developed convolutional neural networks have shown effective and superior performance to perform well on learning high-level and discriminative features in extracting buildings because of the outstanding feature learning and end-to-end pixel labelling abilities. However, it is difficult to use the features of different levels with a certain degree of importance that is appropriate to deep learning networks. To tackle this problem, a network based on U-Nets and the attention mechanism block was proposed. The network contains an encoder part and a decoder part and a spatial attention module. The special architecture presented in this article enhances the propagation of features and effectively utilizes the features at various levels to reduce errors. The other remarkable thing is that attention module blocks only lead to a minimal increase in model complexity. We effectively demonstrate an improvement of building extraction accuracy on challenging Potsdam and Vaihingen benchmark datasets. The results of this paper show that the proposed architecture improves building extraction in very high resolution remote sensing images compared to previous models.

Sign in / Sign up

Export Citation Format

Share Document