“…Teng et al presented a classifierconstrained deep adversarial domain adaptation (CDADA) method exploiting the idea of MCD for cross domain semisupervised classification of RS scene images [130], where a deep convolutional neural network (DCNN) is used to build feature representations and adversarial DA is used to align the feature distribution of domains. Zhang et al proposed a domain feature enhancement network (DFENet) to enhance the discriminative ability of the learned features for dealing with the domain variances of scene classification [131]. Specifically, a context-aware feature refinement module is first designed to recalibrate global and local features by explicitly modeling interdependencies between the channel and spatial for each domain.…”
Traditional remote sensing (RS) image classification methods heavily rely on labeled samples for model training. When labeled samples are unavailable or labeled samples have different distributions from that of the samples to be classified, the classification model may fail. The cross-domain or crossscene remote sensing image classification is developed for this case where an existing image for training and an unknown image from different scenes or domains for classification. The distribution inconsistency problem may be caused by the differences in acquisition environment conditions, acquisition scene, acquisition time or/and changing sensors. To cope with the cross-domain remote sensing image classification problem, many domain adaptation (DA) techniques have been developed. In this article, we review DA methods in the fields of RS, especially hyperspectral image classification, and provide a survey of DA methods into traditional shallow DA methods (e.g., instance-based, featurebased, and classifier-based adaptations) and recently developed deep DA methods (e.g., discrepancy-based and adversarial-based adaptations).
“…Teng et al presented a classifierconstrained deep adversarial domain adaptation (CDADA) method exploiting the idea of MCD for cross domain semisupervised classification of RS scene images [130], where a deep convolutional neural network (DCNN) is used to build feature representations and adversarial DA is used to align the feature distribution of domains. Zhang et al proposed a domain feature enhancement network (DFENet) to enhance the discriminative ability of the learned features for dealing with the domain variances of scene classification [131]. Specifically, a context-aware feature refinement module is first designed to recalibrate global and local features by explicitly modeling interdependencies between the channel and spatial for each domain.…”
Traditional remote sensing (RS) image classification methods heavily rely on labeled samples for model training. When labeled samples are unavailable or labeled samples have different distributions from that of the samples to be classified, the classification model may fail. The cross-domain or crossscene remote sensing image classification is developed for this case where an existing image for training and an unknown image from different scenes or domains for classification. The distribution inconsistency problem may be caused by the differences in acquisition environment conditions, acquisition scene, acquisition time or/and changing sensors. To cope with the cross-domain remote sensing image classification problem, many domain adaptation (DA) techniques have been developed. In this article, we review DA methods in the fields of RS, especially hyperspectral image classification, and provide a survey of DA methods into traditional shallow DA methods (e.g., instance-based, featurebased, and classifier-based adaptations) and recently developed deep DA methods (e.g., discrepancy-based and adversarial-based adaptations).
“…To solve the second problem, unsupervised domain adaptation (UDA) has been commonly considered by recent remote sensing literature ( Tong et al, 2020 , Liu and Qin, 2020 , Zhong et al, 2020 , Zhang et al, 2021b , Ji et al, 2020 , Saha et al, 2022 ). UDA aims to adapt models trained on the source domain to the target domain without supervised information ( Tuia et al, 2016 ).…”
Section: Introductionmentioning
confidence: 99%
“…In contrast, adversarial-based methods, such as the domain-adversarial neural network (DANN) ( Ganin et al, 2016 ) and Adversarial Discriminative Domain Adaptation (ADDA) ( Tzeng et al, 2017 ), do not require manually designed criteria for domain matching. They instead learn criteria by simultaneously training a feature generator and a domain discriminator, which attempt to extract indistinguishable features for both domains and distinguish the features of different domains, respectively ( Zhang et al, 2021b , Ji et al, 2020 ).…”
“…In the spectral grouping and the integration module, the spectral attention mask aimed to integrate the group features [38]. Unlike attention mechanisms, Zhang et al [39] proposed the domain feature enhancement network (DFENet), which builds the dependencies between channels and spaces to calibrate global and local features using a dynamic self-gating mechanism. Feng et al [40] proposed an end-to-end CNN framework based on bandwise-independent convolution and hard thresholding for band selection of HSIs.…”
In the past few years, many convolutional neural networks (CNNs) have been applied to hyperspectral image (HSI) classification. However, many of them have the following drawbacks. 1) They do not fully consider the abundant band spectral information and insufficiently extract the spatial information of HSI. 2) All bands and neighboring pixels are treated equally, so CNNs may learn features from redundant or useless bands/pixels. 3) A significant amount of hidden semantic information is lost when a single-scale convolution kernel is used in CNNs. To alleviate these problems, we propose a Spatial-Spectral Split Attention Residual Networks (S 3 ARN) for HSI classification. In S 3 ARN, a split attention strategy is used to fuse the features extracted from multi-receptive fields, in which both spectral and spatial split attention modules are composed of bottleneck residual blocks. Thanks to the bottleneck structure, the proposed method can effectively prevent overfitting, speeds up the model training, and reduces the network parameters. Moreover, the spectral and spatial attention residual branches aim to generate the attention masks, which can simultaneously emphasize useful bands and neighbor pixels and suppress useless ones. Experimental results on three benchmark datasets demonstrate the effectiveness of the proposed model for HSI classification.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.