Intermediate Domain Prototype Contrastive Adaptation for Spartina alterniflora Segmentation Using Multitemporal Remote Sensing Images

As an invasive plant in wetlands, spartina alterniflora (S.alterniflora) causes immeasurable damage to wetland ecosystems. Observing S.alterniflora using multi-temporal remote sensing data helps us better understand its further development and facilitates effective containment of its invasion trend. However, inconsistent representation across remote sensing data from different time periods poses a challenge. Fortunately, the utilization of Unsupervised Domain Adaptation (UDA) techniques helps in addressing such issues and enables the exploration of rich temporal dimension information in multi-temporal remote sensing data, revealing the spatio-temporal distribution characteristics of S.alterniflora. However, existing UDA methods mostly focus on directly aligning the global or intra-class distribution representations across domains, which overlooks the issue of significant differences between extreme domains and lacks exploration of inter-class relationships. To address these limitations, an Intermediate Domain Prototype Class-level Learning Network (IDPNet) is proposed. IDPNet utilizes dynamically generated intermediate domain features to construct class prototypes while incorporating inter-class information into the prototype construction, achieving the class-centered distribution alignment for adaptation. Moreover, Intermediate Domain Feature Generation Module (IFM) is employed in IDPNet to blend the latent representations from various domains and generate intermediate domain features in real time. Additionally, the hierarchical feature fusion module (HFM) is designed to enable IDPNet to learn more discriminative and robust spatio-temporal distribution features, thereby reducing the loss of information from patches. Experimental results on two cross-year multi-spectral datasets demonstrate that the proposed IDPNet outperforms several state-of-the-art UDA methods.