A Multiscale Dual-Attention based Convolutional Neural Network for Ship Classification in SAR Image

Zhou, Gaoyu; Zhang, Gong; Fang, Zheng; Dai, Qijun

doi:10.1109/icspcc52875.2021.9564861

Cited by 4 publications

(1 citation statement)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, to validate the effectiveness of the proposed method, we conduct a comparative analysis with two conventional classification methods and three latest deep learning-based PolSAR classification methods. In this experiment, two typical classification methods, SVM 22 and AlexNet, 23 as well as three latest methods, CFCANet, 24 MDACNN, 25 and MSFCN 26 were compared. CFCANet is a new complete frequency channel attention network that can directly process noisy remote sensing images and select part of the low-frequency information to interact adequately with the feature map.…”

Section: Experiments Results and Analysismentioning

confidence: 99%

Multi-scale contrastive learning method for PolSAR image classification

Hua,

Wang,

Sun

et al. 2024

J. Appl. Rem. Sens.

View full text Add to dashboard Cite

Although deep learning-based methods have made remarkable achievements in polarimetric synthetic aperture radar (PolSAR) image classification, these methods require a large number of labeled samples. However, for PolSAR image classification, it is difficult to obtain a large number of labeled samples, which requires extensive human labor and material resources. Therefore, a new PolSAR image classification method based on multi-scale contrastive learning is proposed, which can achieve good classification results with only a small number of labeled samples. During the pre-training process, we propose a multi-scale contrastive learning network model that uses the characteristics of the data itself to train the network by contrastive training. In addition, to capture richer feature information, a multi-scale network structure is introduced. In the training process, considering the diversity and complexity of PolSAR images, we design a hybrid loss function combining the supervised and unsupervised information to achieve better classification performance with limited labeled samples. The experimental results on three real PolSAR datasets have demonstrated that the proposed method outperforms other comparison methods, even with limited labeled samples.

show abstract