Remote Sensing Change Detection via Weak Temporal Supervision
This work addresses the costly annotation bottleneck for remote sensing change detection, offering a scalable solution for land cover monitoring, though it is incremental as it builds on existing weak supervision methods.
The paper tackles the problem of semantic change detection in remote sensing by addressing the scarcity of annotated datasets, introducing a weak temporal supervision strategy that leverages additional temporal observations without new annotations, and achieves strong zero-shot and low-data regime performance on extended datasets like FLAIR and IAILD.
Semantic change detection in remote sensing aims to identify land cover changes between bi-temporal image pairs. Progress in this area has been limited by the scarcity of annotated datasets, as pixel-level annotation is costly and time-consuming. To address this, recent methods leverage synthetic data or generate artificial change pairs, but out-of-domain generalization remains limited. In this work, we introduce a weak temporal supervision strategy that leverages additional temporal observations of existing single-temporal datasets, without requiring any new annotations. Specifically, we extend single-date remote sensing datasets with new observations acquired at different times and train a change detection model by assuming that real bi-temporal pairs mostly contain no change, while pairing images from different locations to generate change examples. To handle the inherent noise in these weak labels, we employ an object-aware change map generation and an iterative refinement process. We validate our approach on extended versions of the FLAIR and IAILD aerial datasets, achieving strong zero-shot and low-data regime performance across different benchmarks. Lastly, we showcase results over large areas in France, highlighting the scalability potential of our method.