Learning Temporal Consistency for High Spatial Resolution Remote Sensing Imagery Semantic Change Detection

Semantic change detection (SCD) is a crucial task in remote sensing imagery interpretation, which identifies where the changes are and what categories the objects before and after the changes belong to. Postclassification comparison (PCC), as the simplest method, suffers from severe false alarms. While multitask methods face another issue, in that the changed areas in the binary change map have the same object categories in the semantic maps, i.e., semantic change inconsistency. In this study, we leveraged the commutative property of temporal semantic labels in unchanged areas to generate temporal consistency embedding and propose temporal-semantic feature blending (TSFB), which is a feature interaction operation that can dynamically adjust the distance between bitemporal features by controlling a blending weight. In order to realize adaptive temporal consistency learning, we propose the TEmporal-Semantic feature CalibratiOn (TESCO) module, which can estimate the optimal value of the blending weight for TSFB automatically and make the segmentation network learn temporal consistency from coarse to fine through recurrence and the end-to-end training process. The TESCO module is a plug-and-play module that can be combined with any SCD method. In this study, we added the TESCO module to both PCC and multitask-based SCD methods and conducted comprehensive experiments on three large-scale and different application scenario SCD datasets with different semantic change numbers and time series. The experimental results show that the TESCO module can effectively learn temporal consistency, resulting in a significant improvement in the performance of PCC methods and the semantic consistency of the multitask-based methods. The implementation of the TESCO module will be available at https://github.com/Daisy-7/TESCO