UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

Lightweight Single Image Super-Resolution Through Efficient Second-Order Attention Spindle Network

Chen, Y; Chen, Y; Xue, J-H; Yang, W; Liao, Q; (2020) Lightweight Single Image Super-Resolution Through Efficient Second-Order Attention Spindle Network. In: Proceedings of 2020 IEEE International Conference on Multimedia and Expo (ICME). IEEE: London, UK. Green open access

[thumbnail of YiyunChen-ICME2020.pdf]
Preview
Text
YiyunChen-ICME2020.pdf - Accepted Version

Download (864kB) | Preview

Abstract

Recent years have witnessed great success of applying deep convolutional neural networks (CNNs) to single image superresolution (SISR). However, most of these algorithms focus on increasing modeling capability through developing deeper and wider networks, improving the performance but at a cost of huge computation. Targeting at a better trade-off between efficiency and effectiveness, we propose ESASN, an efficient second-order attention spindle network for lightweight SISR. ESASN is built upon efficient second-order attention spindle (ESAS) blocks, each of which contains two well-designed new modules, efficient multiscale (EMS) module and second-order attention (SOA) module. EMS reduces a considerable number of parameters while retaining the multi-scale structure to explore rich features. SOA further rescales the multi-scale feature maps, capturing the inter-dependencies among channels pixel-wisely with little additional cost. Both qualitative and quantitative experimental results demonstrate that the combination of EMS and SOA works out favorably for SISR, lifting the performance with fewer parameters. Code is available at https://github.com/yiyunchen/ESASN.

Type: Proceedings paper
Title: Lightweight Single Image Super-Resolution Through Efficient Second-Order Attention Spindle Network
Event: 2020 IEEE International Conference on Multimedia and Expo (ICME)
Dates: 06 July 2020 - 10 July 2020
ISBN-13: 978-1-7281-1331-9
Open access status: An open access version is available from UCL Discovery
DOI: 10.1109/icme46284.2020.9102946
Publisher version: https://doi.org/10.1109/icme46284.2020.9102946
Language: English
Additional information: This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions.
Keywords: Lightweight super-resolution, multi-scale features, spindle network, second-order attention
UCL classification: UCL
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Maths and Physical Sciences
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Maths and Physical Sciences > Dept of Statistical Science
URI: https://discovery.ucl.ac.uk/id/eprint/10100829
Downloads since deposit
112Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item