A Transformer-Based Siamese Network for Change Detection
This work addresses remote sensing change detection, offering an incremental improvement over existing methods.
The paper tackles change detection in remote sensing images by proposing ChangeFormer, a transformer-based Siamese network that outperforms previous fully convolutional methods on two datasets.
This paper presents a transformer-based Siamese network architecture (abbreviated by ChangeFormer) for Change Detection (CD) from a pair of co-registered remote sensing images. Different from recent CD frameworks, which are based on fully convolutional networks (ConvNets), the proposed method unifies hierarchically structured transformer encoder with Multi-Layer Perception (MLP) decoder in a Siamese network architecture to efficiently render multi-scale long-range details required for accurate CD. Experiments on two CD datasets show that the proposed end-to-end trainable ChangeFormer architecture achieves better CD performance than previous counterparts. Our code is available at https://github.com/wgcban/ChangeFormer.