Toward Efficient Remote Sensing Image Change Detection via Cross-Temporal Context Learning

Change detection (CD) aims to find areas of specific changes in multitemporal remote sensing images. The existing methods fail to adequately explore the cross-temporal global context, making the establishment of spatial-temporal deep global associations insufficient and inefficient. As a result, their performance is vulnerable to complex and various objects in changing scenes. Hence, we propose a cross-temporal context learning network, termed as CCLNet, where the intratemporal and intertemporal long-range dependencies are mined and interactively fused, to fully exploit the cross-temporal context information. Specifically, a lightweight convolutional neural network (CNN) is first used to extract deep semantic features. Then, a well-designed cross-temporal fusion transformer (CFT) is proposed to locate the changing objects in the scene by establishing the long-range dependence across bitemporal images. Thanks to this, temporal-specific information extraction and cross-temporal information integration are seamlessly integrated into the same network, thereby significantly improving the discriminative features of changing objects. Furthermore, this allows us to use naive backbones with low computational costs to achieve reliable CD performance. Experiments on mainstream benchmarks show that our proposed method can handle CD tasks faster than state-of-the-art (SOTA) methods while maintaining better or comparable matching accuracy on a single RTX3090.