The University of Southampton
University of Southampton Institutional Repository

Inner-imaging networks: Put lenses into convolutional structure

Inner-imaging networks: Put lenses into convolutional structure
Inner-imaging networks: Put lenses into convolutional structure
Despite the tremendous success in computer vision, deep convolutional networks suffer from serious computation costs and redundancies. Although previous works address that by enhancing the diversities of filters, they have not considered the complementarity and the completeness of the internal convolutional structure. To respond to this problem, we propose a novel inner-imaging (InI) architecture, which allows relationships between channels to meet the above requirement. Specifically, we organize the channel signal points in groups using convolutional kernels to model both the intragroup and intergroup relationships simultaneously. A convolutional filter is a powerful tool for modeling spatial relations and organizing grouped signals, so the proposed methods map the channel signals onto a pseudoimage, like putting a lens into the internal convolution structure. Consequently, not only is the diversity of channels increased but also the complementarity and completeness can be explicitly enhanced. The proposed architecture is lightweight and easy to be implement. It provides an efficient self-organization strategy for convolutional networks to improve their performance. Extensive experiments are conducted on multiple benchmark datasets, including CIFAR, SVHN, and ImageNet. Experimental results verify the effectiveness of the InI mechanism with the most popular convolutional networks as the backbones.
Channelwise attention, Computational modeling, Computer architecture, Computer science, Convolution, Lenses, Redundancy, Shape, convolutional networks, grouped relationships, inner-imaging (InI)
2168-2267
Hu, Yang
8a6ae98d-ea5a-4d97-86b2-4ba64fe2094f
Wen, Guihua
411fd94f-89bd-4ad7-908d-9c876afd7564
Luo, Mingnan
43faccbb-eead-4787-af0f-d3fbe7f2538b
Dai, Dan
85b7cbb9-cd58-46e1-b7ff-c264e9f46908
Cao, Wenming
c7b5ae8d-2923-4138-a6bb-ce718679bd68
Yu, Zhiwen
1421a503-983b-460b-8372-e2df423f6890
Hall, Wendy
11f7f8db-854c-4481-b1ae-721a51d8790c
Hu, Yang
8a6ae98d-ea5a-4d97-86b2-4ba64fe2094f
Wen, Guihua
411fd94f-89bd-4ad7-908d-9c876afd7564
Luo, Mingnan
43faccbb-eead-4787-af0f-d3fbe7f2538b
Dai, Dan
85b7cbb9-cd58-46e1-b7ff-c264e9f46908
Cao, Wenming
c7b5ae8d-2923-4138-a6bb-ce718679bd68
Yu, Zhiwen
1421a503-983b-460b-8372-e2df423f6890
Hall, Wendy
11f7f8db-854c-4481-b1ae-721a51d8790c

Hu, Yang, Wen, Guihua, Luo, Mingnan, Dai, Dan, Cao, Wenming, Yu, Zhiwen and Hall, Wendy (2021) Inner-imaging networks: Put lenses into convolutional structure. IEEE Transactions on Cybernetics. (doi:10.1109/TCYB.2020.3034605).

Record type: Article

Abstract

Despite the tremendous success in computer vision, deep convolutional networks suffer from serious computation costs and redundancies. Although previous works address that by enhancing the diversities of filters, they have not considered the complementarity and the completeness of the internal convolutional structure. To respond to this problem, we propose a novel inner-imaging (InI) architecture, which allows relationships between channels to meet the above requirement. Specifically, we organize the channel signal points in groups using convolutional kernels to model both the intragroup and intergroup relationships simultaneously. A convolutional filter is a powerful tool for modeling spatial relations and organizing grouped signals, so the proposed methods map the channel signals onto a pseudoimage, like putting a lens into the internal convolution structure. Consequently, not only is the diversity of channels increased but also the complementarity and completeness can be explicitly enhanced. The proposed architecture is lightweight and easy to be implement. It provides an efficient self-organization strategy for convolutional networks to improve their performance. Extensive experiments are conducted on multiple benchmark datasets, including CIFAR, SVHN, and ImageNet. Experimental results verify the effectiveness of the InI mechanism with the most popular convolutional networks as the backbones.

Text
Inner-Imaging_Networks_Put_Lenses_Into_Convolutional_Structure - Accepted Manuscript
Download (3MB)
Text
Inner-Imaging_Networks_Put_Lenses_Into_Convolutional_Structure (1) - Version of Record
Restricted to Repository staff only
Request a copy

More information

Accepted/In Press date: 25 October 2020
e-pub ahead of print date: 15 August 2021
Published date: 16 August 2021
Additional Information: Publisher Copyright: IEEE
Keywords: Channelwise attention, Computational modeling, Computer architecture, Computer science, Convolution, Lenses, Redundancy, Shape, convolutional networks, grouped relationships, inner-imaging (InI)

Identifiers

Local EPrints ID: 452199
URI: http://eprints.soton.ac.uk/id/eprint/452199
ISSN: 2168-2267
PURE UUID: 74144687-662f-421d-8f24-97e8118d016e
ORCID for Wendy Hall: ORCID iD orcid.org/0000-0003-4327-7811

Catalogue record

Date deposited: 29 Nov 2021 17:33
Last modified: 17 Mar 2024 02:32

Export record

Altmetrics

Contributors

Author: Yang Hu
Author: Guihua Wen
Author: Mingnan Luo
Author: Dan Dai
Author: Wenming Cao
Author: Zhiwen Yu
Author: Wendy Hall ORCID iD

Download statistics

Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.

View more statistics

Atom RSS 1.0 RSS 2.0

Contact ePrints Soton: eprints@soton.ac.uk

ePrints Soton supports OAI 2.0 with a base URL of http://eprints.soton.ac.uk/cgi/oai2

This repository has been built using EPrints software, developed at the University of Southampton, but available to everyone to use.

We use cookies to ensure that we give you the best experience on our website. If you continue without changing your settings, we will assume that you are happy to receive cookies on the University of Southampton website.

×