.png){kind=icon}
返回
Self-Supervised Learning With Multiscale Densely Connected Network for Hyperspectral Image Classification
.png){kind=icon}
PRE
AI
DOI：10.1109/TGRS.2024.3424394.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
In recent years, deep learning-based methods have exhibited remarkable performance in the field of hyperspectral image (HSI) classification. However, conventional supervised methods heavily rely on a substantial number of labeled samples. Self-supervised learning, as a prominent unsupervised representation learning technique, offers the potential to extract valuable information from unlabeled data. In this article, we introduce a novel unsupervised approach called self-supervised learning with the multiscale densely connected network (SS-MSDCNet) to make full use of unlabeled samples for HSI classification. First, a two-stream structure was designed to generate more positive pairs, which enables the contrast self-supervised training to learn more useful information from unlabeled data. Subsequently, a data augmentation technique based on spectral splitting was proposed to coordinate the two-stream structure of SS-MSDCNet, enhancing spectral information expression. The backbone of the proposed approach is the multiscale densely connected network (MSDCNet), which obtains input HSIs with various spatial scales by removing peripheral pixels from the original input and subsequently extracts multiscale spatial-spectral features using 3-D densely connected modules and 3-D spatial attention modules. The 3-D densely connected module effectively harnesses multiscale features extracted by various convolutional layers, while the 3-D spatial attention module enhances the network's focus on features conducive to accurate classification. To validate the efficacy of our approach, we conducted extensive experiments using four distinct HSI datasets. The results unequivocally demonstrate that SS-MSDCNet outperforms several well-established supervised and unsupervised classification methods. Furthermore, we designed a transfer experiment to confirm SS-MSDCNet's robust generalization capabilities. The code is available at https://github.com/mrblank99/SS-MSDCNet.
Keyword:
Feature extraction
Self-supervised learning
Training
Three-dimensional displays
Task analysis
Data augmentation
Data mining
DenseNet
hyperspectral image classification
multiscale fusion
self-supervised learning
unsupervised learning
期刊
IF:
8.6
论文数:
2.1W
被引数:
10.7W
机构
引用论文
.png){kind=icon}
Adaptive Domain-Adversarial Few-Shot Learning for Cross-Domain Hyperspectral Image Classification自适应域对抗性少镜头学习的跨域高光谱图像分类
PREAI
分享收藏Local Manifold Learning-Based k-Nearest-Neighbor for Hyperspectral Image Classification基于局部流形学习的k近邻高光谱图像分类
PREAI
分享收藏Hyperspectral Image Classification Using Dictionary-Based Sparse Representation基于字典稀疏表示的高光谱图像分类
PREAI
分享收藏ALPN: Active-Learning-Based Prototypical Network for Few-Shot Hyperspectral Imagery Classification
PREAI
分享收藏Dual-Stream Class-Adaptive Network for Semi-Supervised Hyperspectral Image Classification用于半监督高光谱图像分类的双流类自适应网络
PREAI
分享收藏Learning and Transferring Deep Joint Spectral-Spatial Features for Hyperspectral Classification面向高光谱分类的深度光谱-空间联合特征学习与转移
PREAI
分享收藏Unsupervised Spatial-Spectral Feature Learning by 3D Convolutional Autoencoder for Hyperspectral Classification基于3D卷积自动编码器的无监督空间光谱特征学习，用于高光谱分类
PREAI
分享收藏
查看更多内容