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.
@article{arxiv.2201.01293,
title = {A Transformer-Based Siamese Network for Change Detection},
author = {Wele Gedara Chaminda Bandara and Vishal M. Patel},
journal= {arXiv preprint arXiv:2201.01293},
year = {2022}
}
Comments
Accepted to International Geoscience and Remote Sensing Symposium (IGARSS), 2022. 4 pages, 2 figures. Code & trained models are available at https://github.com/wgcban/ChangeFormer