Transformer Meets Convolution: A Bilateral Awareness Network for Semantic Segmentation of Very Fine Resolution Urban Scene Images

1 code implementation • 23 Jun 2021 • Libo Wang, Rui Li, Dongzhi Wang, Chenxi Duan, Teng Wang, Xiaoliang Meng

Specifically, the dependency path is conducted based on the ResT, a novel Transformer backbone with memory-efficient multi-head self-attention, while the texture path is built on the stacked convolution operation.

Autonomous Driving Decision Making +3