Semantic segmentation using stride spatial pyramid pooling and dual attention decoder

Chengli Peng, Jiayi Ma

Abstract: Highlights•We propose an SSPP structure to capture multiscale semantic information.•Attention mechanism is applied to bridge the information gap in segmentation networks.•We propose a new decoder to make full use of the low- and high-level feature maps.•Auxiliary loss is applied to make the network easier to train.•Our method attains state-of-the-art performance on PASCAL VOC 2012, Cityscapes and COCO-Stuff.