Pyramid attention network for semantic segmentation

Hanchao Li, Pengfei Xiong, Jie An, Lingxue Wang*

*Corresponding author for this work

Research output: Contribution to conferencePaperpeer-review

88 Citations (Scopus)

Abstract

A Pyramid Attention Network(PAN) is proposed to exploit the impact of global contextual information in semantic segmentation. Different from most existing works, we combine attention mechanism and spatial pyramid to extract precise dense features for pixel labeling instead of complicated dilated convolution and artificially designed decoder networks. Specifically, we introduce a Feature Pyramid Attention module to perform spatial pyramid attention structure on high-level output and combine global pooling to learn a better feature representation, and a Global Attention Upsample module on each decoder layer to provide global context as a guidance of low-level features to select category localization details. The proposed approach achieves state-of-the-art performance on PASCAL VOC 2012 and Cityscapes benchmarks with a new record of mIoU accuracy 84.0% on PASCAL VOC 2012, while training without COCO dataset.

Original languageEnglish
Publication statusPublished - 2019
Event29th British Machine Vision Conference, BMVC 2018 - Newcastle, United Kingdom
Duration: 3 Sept 20186 Sept 2018

Conference

Conference29th British Machine Vision Conference, BMVC 2018
Country/TerritoryUnited Kingdom
CityNewcastle
Period3/09/186/09/18

Fingerprint

Dive into the research topics of 'Pyramid attention network for semantic segmentation'. Together they form a unique fingerprint.

Cite this