Deep interleaved network for image super-resolution with asymmetric co-attention

Feng LI, Runmin CONG, Huihui BAI*, Yifan HE

*Corresponding author for this work

Research output: Book Chapters | Papers in Conference ProceedingsConference paper (refereed)Referred Conference Paperpeer-review

14 Citations (Scopus)

Abstract

Recently, Convolutional Neural Networks (CNN) based image super-resolution (SR) have shown significant success in the literature. However, these methods are implemented as single-path stream to enrich feature maps from the input for the final prediction, which fail to fully incorporate former low-level features into later high-level features. In this paper, to tackle this problem, we propose a deep interleaved network (DIN) to learn how information at different states should be combined for image SR where shallow information guides deep representative features prediction. Our DIN follows a multi-branch pattern allowing multiple interconnected branches to interleave and fuse at different states. Besides, the asymmetric co-attention (AsyCA) is proposed and attacked to the interleaved nodes to adaptively emphasize informative features from different states and improve the discriminative ability of networks. Extensive experiments demonstrate the superiority of our proposed DIN in comparison with the state-of-the-art SR methods.

Original languageEnglish
Title of host publicationProceedings of the 29th International Joint Conference on Artificial Intelligence, IJCAI 2020
EditorsChristian BESSIERE
PublisherInternational Joint Conferences on Artificial Intelligence
Pages537-543
Number of pages7
ISBN (Electronic)9780999241165
DOIs
Publication statusPublished - Mar 2021
Externally publishedYes
Event29th International Joint Conference on Artificial Intelligence, IJCAI 2020 - Yokohama, Japan
Duration: 7 Jan 202115 Jan 2021

Publication series

NameIJCAI International Joint Conference on Artificial Intelligence
Volume2021-January
ISSN (Print)1045-0823

Conference

Conference29th International Joint Conference on Artificial Intelligence, IJCAI 2020
Country/TerritoryJapan
CityYokohama
Period7/01/2115/01/21

Bibliographical note

Publisher Copyright:
© 2020 Inst. Sci. inf., Univ. Defence in Belgrade. All rights reserved.

Fingerprint

Dive into the research topics of 'Deep interleaved network for image super-resolution with asymmetric co-attention'. Together they form a unique fingerprint.

Cite this