Attention-Based Multiscale Residual Adaptation Network for Cross-Scene Classification
Attention-Based Multiscale Residual Adaptation Network for Cross-Scene Classification
复制标题
用于跨场景分类的基于注意力的多尺度残差适应网络
DOI：
10.1109/tgrs.2021.3056624
复制
发表时间：
2021-03
影响因子：
8.2
通讯作者：
Xue Li
中科院分区：
文献类型：
--
作者：
Sihan Zhu;Bo Du;Liangpei Zhang;Xue Li
近年来，分类越来越受到人们的关注，并已应用于遥感领域的许多领域，包括土地利用、森林监测、城市规划和植被管理。针对标记数据不足和监督模型泛化能力差的问题，提出了跨场景分类方法，以更好地利用已有知识。现有的跨场景自适应分类方法只考虑了边缘分布，而条件分布在真实的应用中同样重要。此外，基于深度学习的方法会对齐从单尺度结构中提取的特征分布，导致信息丢失。为了克服上述缺点，提出了一种基于注意力的多尺度残差自适应网络（AMRAN）的跨场景分类任务。在建议的AMRAN，边际和条件分布都考虑到更全面的对齐。此外，注意力机制和多尺度策略分别用于提取更强大的功能和更完整的信息。在四个场景分类数据集上的实验结果表明，AMRAN算法与现有的深度自适应方法相比，具有显著的改进效果。
In recent years, classification has obtained ever-rising attention and has been applied to many areas in the field of remote sensing, including land use, forest monitoring, urban planning, and vegetation management. Due to the lack of labeled data and the poor generalization ability of supervised models, cross-scene classification is proposed for better utilization of the existing knowledge. Existing adaptation methods for cross-scene classification only consider the marginal distribution, while the conditional distribution is equally important in real applications. In addition, approaches based on deep learning align the distribution of features extracted from a single-scale structure, leading to the loss of information. To overcome the above drawbacks, an Attention-based Multiscale Residual Adaptation Network (AMRAN) is proposed for cross-scene classification tasks. In the proposed AMRAN, both the marginal and conditional distributions are taken into consideration for more comprehensive alignment. Besides, the attention mechanism and the multiscale strategy are used to extract more robust features and more complete information, respectively. Experimental results between four existing scene classification data sets demonstrate that AMRAN has a significant improvement compared with the state-of-the-art deep adaptation methods.
登录
查看更多内容
影响因子：
7.8
作者：
Zhu, Yongchun;Zhuang, Fuzhen;He, Qing
通讯作者：
He, Qing
DOI：
10.1609/aaai.v33i01.33015345
发表时间：
2019-07
期刊：
--
影响因子：
--
作者：
Ximei Wang;Liang Li;Weirui Ye;Mingsheng Long;Jianmin Wang
通讯作者：
Ximei Wang;Liang Li;Weirui Ye;Mingsheng Long;Jianmin Wang
DOI：
10.1109/igarss.2018.8517487
发表时间：
2018-07
期刊：
IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium
影响因子：
--
作者：
Laila Bashmal;Y. Bazi;H. Alhichri;N. Alajlan
通讯作者：
Laila Bashmal;Y. Bazi;H. Alhichri;N. Alajlan
DOI：
--
发表时间：
2010-07
期刊：
--
影响因子：
--
作者：
Gui-Song Xia;Wen Yang;J. Delon;Y. Gousseau;Hong Sun;H. Maître
通讯作者：
Gui-Song Xia;Wen Yang;J. Delon;Y. Gousseau;Hong Sun;H. Maître
DOI：
--
发表时间：
2014-09
期刊：
--
影响因子：
--
作者：
Yaroslav Ganin;V. Lempitsky
通讯作者：
Yaroslav Ganin;V. Lempitsky