Inner-Imaging Networks : Put Lenses Into Convolutional Structure

Research output: Journal Publications and ReviewsRGC 21 - Publication in refereed journalpeer-review

4 Scopus Citations
View graph of relations

Author(s)

  • Yang Hu
  • Guihua Wen
  • Mingnan Luo
  • Dan Dai
  • Zhiwen Yu
  • Wendy Hall

Related Research Unit(s)

Detail(s)

Original languageEnglish
Pages (from-to)8547-8560
Journal / PublicationIEEE Transactions on Cybernetics
Volume52
Issue number8
Online published16 Aug 2021
Publication statusPublished - Aug 2022

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.

Research Area(s)

  • Channelwise attention, Computational modeling, Computer architecture, Computer science, Convolution, convolutional networks, grouped relationships, inner-imaging (InI), Lenses, Redundancy, Shape

Citation Format(s)

Inner-Imaging Networks: Put Lenses Into Convolutional Structure. / Hu, Yang; Wen, Guihua; Luo, Mingnan et al.
In: IEEE Transactions on Cybernetics, Vol. 52, No. 8, 08.2022, p. 8547-8560.

Research output: Journal Publications and ReviewsRGC 21 - Publication in refereed journalpeer-review