MASNet:Improve Performance of Siamese Networks with Mutual-attention for Remote Sensing Change Detection Tasks
This work addresses a specific bottleneck in remote sensing change detection, offering an incremental improvement for applications in environmental monitoring and urban planning.
The paper tackled the problem of early-stage information exchange in Siamese networks for remote sensing change detection by introducing a mutual-attention plug-in, resulting in improved performance on multiple datasets for both CNN and ViT architectures.
Siamese networks are widely used for remote sensing change detection tasks. A vanilla siamese network has two identical feature extraction branches which share weights, these two branches work independently and the feature maps are not fused until about to be sent to a decoder head. However we find that it is critical to exchange information between two feature extraction branches at early stage for change detection task. In this work we present Mutual-Attention Siamese Network (MASNet), a general siamese network with mutual-attention plug-in, so to exchange information between the two feature extraction branches. We show that our modification improve the performance of siamese networks on multi change detection datasets, and it works for both convolutional neural network and visual transformer.