Hybrid Attention-Based Encoder–Decoder Fully Convolutional Network for PolSAR Image Classification

Recently, methods based on convolutional neural networks (CNNs) achieve superior performance in polarimetric synthetic aperture radar (PolSAR) image classification. However, the current CNN-based classifiers follow patch-based frameworks, which need input images to be divided into overlapping patche...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Remote sensing (Basel, Switzerland) Ročník 15; číslo 2; s. 526
Hlavní autoři: Fang, Zheng, Zhang, Gong, Dai, Qijun, Xue, Biao, Wang, Peng
Médium: Journal Article
Jazyk:angličtina
Vydáno: Basel MDPI AG 01.01.2023
Témata:
Artificial neural networks
Classification
Coders
Decomposition
Feature extraction
Feature selection
fully convolutional neural network (FCN)
hybrids
image analysis
Image classification
Modules
Neural networks
Performance enhancement
polarimetric synthetic aperture radar (PolSAR)
polarimetry
Radar imaging
Receptive field
self-attention
Semantics
Synthetic aperture radar
ISSN:2072-4292, 2072-4292
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Recently, methods based on convolutional neural networks (CNNs) achieve superior performance in polarimetric synthetic aperture radar (PolSAR) image classification. However, the current CNN-based classifiers follow patch-based frameworks, which need input images to be divided into overlapping patches. Consequently, these classification approaches have the drawback of requiring repeated calculations and only relying on local information. In addition, the receptive field size in conventional CNN-based methods is fixed, which limits the potential to extract features. In this paper, a hybrid attention-based encoder–decoder fully convolutional network (HA-EDNet) is presented for PolSAR classification. Unlike traditional CNN-based approaches, the encoder–decoder fully convolutional network (EDNet) can use an arbitrary-size image as input without dividing. Then, the output is the whole image classification result. Meanwhile, the self-attention module is used to establish global spatial dependence and extract context characteristics, which can improve the performance of classification. Moreover, an attention-based selective kernel module (SK module) is included in the network. In the module, softmax attention is employed to fuse several branches with different receptive field sizes. Consequently, the module can capture features with different scales and further boost classification accuracy. The experiment results demonstrate that the HA-EDNet achieves superior performance compared to CNN-based and traditional fully convolutional network methods.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:2072-4292
2072-4292
DOI:10.3390/rs15020526