当前位置: X-MOL 学术J. Appl. Remote Sens. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Joint learning using multiscale attention-enhanced features for remote sensing image scene classification
Journal of Applied Remote Sensing ( IF 1.7 ) Pub Date : 2022-07-01 , DOI: 10.1117/1.jrs.16.036506
Donghang Yu, Qing Xu, Xiangyun Liu, Liang Lv, Haitao Guo, Jun Lu, Yuzhun Lin

Scene classification is an important tool for remote sensing image interpretation, and it has fundamental applications in research and industry. However, given complex backgrounds and scale variations, remote sensing images have large intraclass diversity and interclass similarity, which bring challenges to accurate classification of remote sensing images. We proposed a scene classification method using joint learning and multiscale attention to alleviate the aforementioned problems. To fully utilize the multiscale information of the image and improve the adaptability of the proposed method to objects with various sizes, different from general methods that fuse different scales of features for classification, joint learning using multiscale features is developed to optimize the whole network. Specifically, we leverage a pretrained deep convolutional neural network as the feature extractor to extract low-level, medium-level, and high-level feature maps from the images. Then, due to the poor semantics of low-level and medium-level feature maps compared with the high-level feature maps, we design a multiscale attention module to enhance the semantic information and suppress the noise information. Finally, the global mean pooling is used to obtain the feature vectors and different classifiers are used for different feature vectors. And the decision-level fusion is adopted to obtain more reliable predictions. The experimental results on the AID and NWPU-RESISC45 datasets show that the proposed method makes a significant improvement in terms of overall accuracies compared with the baselines. And the overall accuracies of our method on the two datasets are 97.49% and 95.20%, respectively, which achieves state-of-the-art performance. The code will be public at a Github repository available at https://github.com/Cbanyungong/JLMSAF.

中文翻译:

利用多尺度注意力增强特征进行遥感图像场景分类的联合学习

场景分类是遥感图像解译的重要工具,在研究和工业中具有基础性的应用。然而,鉴于复杂的背景和尺度变化,遥感图像具有较大的类内多样性和类间相似性,这给遥感图像的准确分类带来了挑战。我们提出了一种使用联合学习和多尺度注意力的场景分类方法来缓解上述问题。为了充分利用图像的多尺度信息,提高所提方法对各种尺寸对象的适应性,不同于一般的融合不同尺度特征进行分类的方法,开发了利用多尺度特征的联合学习来优化整个网络。具体来说,我们利用预训练的深度卷积神经网络作为特征提取器,从图像中提取低级、中级和高级特征图。然后,由于低级和中级特征图与高级特征图相比语义较差,我们设计了一个多尺度注意模块来增强语义信息并抑制噪声信息。最后,使用全局均值池化来获得特征向量,并针对不同的特征向量使用不同的分类器。并采用决策级融合来获得更可靠的预测。在 AID 和 NWPU-RESISC45 数据集上的实验结果表明,与基线相比,所提出的方法在整体精度方面有显着提高。我们的方法在两个数据集上的总体准确率分别为 97.49% 和 95.20%,达到了最先进的性能。该代码将在 https://github.com/Cbanyungong/JLMSAF 的 Github 存储库中公开。
更新日期:2022-07-01
down
wechat
bug