Multiple Attention Network for Spartina alterniflora Segmentation Using Multitemporal Remote Sensing Images

The semantic segmentation of multitemporal remote sensing images to construct wetland land surface coverage is the basis for the perception and dynamic modeling of geographic scenes. However, the segmentation of Spartina alterniflora in remote sensing images on wetlands faces the problems such as a low level of cooperative interpretation in multitemporal images and high fragmentation in the distribution of S. alterniflora. To solve the issues, a multiple attention network (MARNet) based on transfer learning is proposed. The method is designed with a plug-and-play attention module to enhance the learning of vegetation features and improve the network's ability to focus on small areas of S. alterniflora. At the same time, MARNet designs the transfer learning architecture from both interdomain alignment and intradomain adaptation perspectives, aligning the statistical distribution by using the maximum mean difference (MMD) between the source and target domains (TDs), and entropy minimization within the domain of the TD to enhance the high confidence prediction of this domain. In addition, since the samples have a serious imbalance problem, redundant cutting and splicing steps are employed for the prediction results to prevent the poor edge prediction of some image blocks. Experimental results on three cross-year RSI datasets demonstrate that the proposed MARNet performs significantly better than other networks and is able to extract S. alterniflora in wetlands more accurately.