Efficient CNN with uncorrelated Bag of Features pooling

Firas Laakom, Jenni Raitoharju, Alexandros Iosifidis, Moncef Gabbouj

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

2 Citations (Scopus)

Abstract

Despite the superior performance of CNN, deploying them on low computational power devices is still limited as they are typically computationally expensive. One key cause of the high complexity is the connection between the convolution layers and the fully connected layers, which typically requires a high number of parameters. To alleviate this issue, Bag of Features (BoF) pooling has been recently proposed. BoF learns a dictionary, that is used to compile a histogram representation of the input. In this paper, we propose an approach that builds on top of BoF pooling to boost its efficiency by ensuring that the items of the learned dictionary are non-redundant. We propose an additional loss term, based on the pair-wise correlation of the items of the dictionary, which complements the standard loss to explicitly regularize the model to learn a more diverse and rich dictionary. The proposed strategy yields an efficient variant of BoF and further boosts its performance, without any additional parameters.

Original languageEnglish
Title of host publication2022 IEEE Symposium Series on Computational Intelligence (SSCI)
EditorsHisao Ishibuchi, Chee-Keong Kwoh, Ah-Hwee Tan, Dipti Srinivasan, Chunyan Miao, Anupam Trivedi, Keeley Crockett
PublisherIEEE
Pages1082-1087
Number of pages6
ISBN (Electronic)9781665487689
DOIs
Publication statusPublished - 2022
Publication typeA4 Article in conference proceedings
EventIEEE Symposium Series on Computational Intelligence (SSCI) - Singapore, Singapore
Duration: 4 Dec 20227 Dec 2022

Publication series

NameIEEE Symposium Series on Computational Intelligence
ISSN (Electronic)2472-8322

Conference

ConferenceIEEE Symposium Series on Computational Intelligence (SSCI)
Country/TerritorySingapore
CitySingapore
Period4/12/227/12/22

Keywords

  • bag of features pooling
  • CNN
  • deep learning
  • diversity

Publication forum classification

  • Publication forum level 1

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Science Applications
  • Decision Sciences (miscellaneous)
  • Computational Mathematics
  • Control and Optimization
  • Transportation

Fingerprint

Dive into the research topics of 'Efficient CNN with uncorrelated Bag of Features pooling'. Together they form a unique fingerprint.

Cite this