Bilateral attention decoder: A lightweight decoder for real-time semantic segmentation

Chengli Peng, Tian Tian, Chen Chen, Xiaojie Guo, Jiayi Ma

Abstract: Highlights•We propose a refinement block to improve the information capturing ability of feature maps.•We develop a pooling fusion block to take full advantages of different level feature maps.•Combining two blocks, we propose a lightweight decoder for real-time semantic segmentation.•Our method can attain state-of-the-art accuracy and speed on Cityscapes and Camvid datasets.