Deep hierarchical transformer for change detection in high-resolution remote sensing images

ABSTRACT

Deep learning instantiated by convolutional neural networks has achieved great success in high-resolution remote-sensing image change detection. However, such networks have a limited receptive field, being unable to extract long-range dependencies in a scene. As the transformer model with self-attention can better describe long-range dependencies, we introduce a hierarchical transformer model to improve the precision of change detection in high-resolution remote sensing images. First, the hierarchical transformer extracts abstract features from multitemporal remote sensing images. To effectively minimize the model’s complexity and enhance the feature representation, we limit the self-attention calculation of each transformer layer to local windows with different sizes. Then, we combine the features extracted by the hierarchical transformer and input them into a nested U-Net to obtain the change detection results. Furthermore, a simple but effective model fusion strategy is adopted to improve the change detection accuracy. Extensive experiments are carried out on two large-scale data sets for change detection, LEVIR-CD and SYSU-CD. The quantitative and qualitative experimental results suggest that the proposed method outperforms the advanced methods in terms of detection performance.

KEYWORDS:

• Remote sensing image
• change detection
• deep learning
• hierarchical transformer
• nested U-Net
• model fusion

Disclosure statement

No potential conflict of interest was reported by the authors.

Data availability statement

The data employed in this paper include LEVIR-CD and SYSU-CD. The LEVIR-CD access URL for https://justchenhao.github.io/LEVIR/. The SYSU-CD access URL for https://hub.fastgit.org/liumency/SYSU-CD.

Additional information

Funding

The work was supported by the the Natural Science Foundation of Henan [41201477].