Channelized Axial Attention - Considering Channel Relation within Spatial Attention for Semantic Segmentation

Ye Huang, Di Kang, Wenjing Jia, Liu Liu, Xiangjian He

Research output: Chapter in Book/Conference proceedingConference contributionpeer-review

Abstract

Spatial and channel attentions, modelling the semantic interdependencies in spatial and channel dimensions respectively, have recently been widely used for semantic segmentation. However, computing spatial and channel attentions separately sometimes causes errors, especially for those difficult cases. In this paper, we propose Channelized Axial Attention (CAA) to seamlessly integrate channel attention and spatial attention into a single operation with negligible computation overhead. Specifically, we break down the dot-product operation of the spatial attention into two parts and insert channel relation in between, allowing for independently optimized channel attention on each spatial location. We further develop grouped vectorization, which allows our model to run with very little memory consumption without slowing down the running speed. Comparative experiments conducted on multiple benchmark datasets, including Cityscapes, PASCAL Context, and COCO-Stuff, demonstrate that our CAA outperforms many state-of-the-art segmentation models (including dual attention) on all tested datasets.

Original languageEnglish
Title of host publicationAAAI-22 Technical Tracks 1
PublisherAssociation for the Advancement of Artificial Intelligence
Pages843-851
Number of pages9
ISBN (Electronic)1577358767, 9781577358763
Publication statusPublished - 30 Jun 2022
Externally publishedYes
Event36th AAAI Conference on Artificial Intelligence, AAAI 2022 - Virtual, Online
Duration: 22 Feb 20221 Mar 2022

Publication series

NameProceedings of the 36th AAAI Conference on Artificial Intelligence, AAAI 2022
Volume36

Conference

Conference36th AAAI Conference on Artificial Intelligence, AAAI 2022
CityVirtual, Online
Period22/02/221/03/22

ASJC Scopus subject areas

  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'Channelized Axial Attention - Considering Channel Relation within Spatial Attention for Semantic Segmentation'. Together they form a unique fingerprint.

Cite this