Rethinking Transformers for Semantic Segmentation of Remote Sensing Images

Transformer has been widely applied in image processing tasks as a substitute for convolutional neural networks (CNNs) for feature extraction due to its superiority in global context modeling and flexibility in model generalization. However, the existing transformer-based methods for semantic segmentation of remote sensing (RS) images are still with several limitations, which can be summarized into two main aspects: 1) the transformer encoder is generally combined with CNN-based decoder, leading to inconsistency in feature representations; and 2) the strategies for global and local context information utilization are not sufficiently effective. Therefore, in this article, a global-local transformer segmentor (GLOTS) framework is proposed for the semantic segmentation of RS images to acquire consistent feature representations by adopting transformers for both encoding and decoding, in which a masked image modeling (MIM) pretrained transformer encoder is adopted to learn semantic-rich representations of input images and a multiscale global-local transformer decoder is designed to fully exploit the global and local features. Specifically, the transformer decoder uses a feature separation-aggregation module (FSAM) to utilize the feature adequately at different scales and adopts a global-local attention module (GLAM) containing global attention block (GAB) and local attention block (LAB) to capture the global and local context information, respectively. Furthermore, a learnable progressive upsampling strategy (LPUS) is proposed to restore the resolution progressively, which can flexibly recover the fine-grained details in the upsampling process. The experiment results on the three benchmark RS datasets demonstrate that the proposed GLOTS is capable of achieving better performance with some state-of-the-art methods, and the superiority of the proposed framework is also verified by ablation studies. The code will be available at https://github.com/lyhnsn/GLOTS.

Automated summary

In this article, a global-local transformer segmentor (GLOTS) framework is proposed for the semantic segmentation of remote sensing (RS) images, which adopts transformers for both encoding and decoding to acquire consistent feature representations and fully exploit global and local features. Experimental results demonstrate that the proposed GLOTS achieves better performance on three benchmark RS datasets.