UNetFormer: A UNet-like transformer for efficient semantic segmentation of remote sensing urban scene imagery
UNetFormer: A UNet-like transformer for efficient semantic segmentation of remote sensing urban scene imagery
Libo Wang,Rui Li,4 Autores,P. Atkinson
2021 · DOI: 10.1016/j.isprsjprs.2022.06.008
Isprs Journal of Photogrammetry and Remote Sensing · 864 Citações
TLDR
A Transformer-based decoder and construct a UNet-like Transformer (UNetFormer) for real-time urban scene segmentation, selecting the lightweight ResNet18 as the encoder and developing an efficient global-local attention mechanism to model both global and local information in the decoder.