UNetFormer: a UNet-like transformer for efficient semantic segmentation of remote sensing urban scene imagery

Wang, Libo; Li, Rui; Zhang, Ce ORCID:; Fang, Shenghui; Duan, Chenxi; Meng, Xiaoliang; Atkinson, Peter M.. 2022 UNetFormer: a UNet-like transformer for efficient semantic segmentation of remote sensing urban scene imagery. ISPRS Journal of Photogrammetry and Remote Sensing, 190. 196-214.

Full text not available from this repository.


Semantic segmentation of remotely sensed urban scene images is required in a wide range of practical applications, such as land cover mapping, urban change detection, environmental protection, and economic assessment. Driven by rapid developments in deep learning technologies, the convolutional neural network (CNN) has dominated semantic segmentation for many years. CNN adopts hierarchical feature representation, demonstrating strong capabilities for information extraction. However, the local property of the convolution layer limits the network from capturing the global context. Recently, as a hot topic in the domain of computer vision, Transformer has demonstrated its great potential in global information modelling, boosting many vision-related tasks such as image classification, object detection, and particularly semantic segmentation. In this paper, we propose a Transformer-based decoder and construct an UNet-like Transformer (UNetFormer) for real-time urban scene segmentation. For efficient segmentation, the UNetFormer selects the lightweight ResNet18 as the encoder and develops an efficient global–local attention mechanism to model both global and local information in the decoder. Extensive experiments reveal that our method not only runs faster but also produces higher accuracy compared with state-of-the-art lightweight models. Specifically, the proposed UNetFormer achieved 67.8% and 52.4% mIoU on the UAVid and LoveDA datasets, respectively, while the inference speed can achieve up to 322.4 FPS with a 512 × 512 input on a single NVIDIA GTX 3090 GPU. In further exploration, the proposed Transformer-based decoder combined with a Swin Transformer encoder also achieves the state-of-the-art result (91.3% F1 and 84.1% mIoU) on the Vaihingen dataset. The source code will be freely available at

Item Type: Publication - Article
Digital Object Identifier (DOI):
UKCEH and CEH Sections/Science Areas: Soils and Land Use (Science Area 2017-)
ISSN: 0924-2716
Additional Keywords: semantic segmentation, remote sensing, vision transformer, fully transformer network, global-local context, urban scene
NORA Subject Terms: Computer Science
Data and Information
Related URLs:
Date made live: 22 Jan 2024 15:56 +0 (UTC)

Actions (login required)

View Item View Item

Document Downloads

Downloads for past 30 days

Downloads per month over past year

More statistics for this item...