A4 Article in conference proceedings
Efficient CNN with uncorrelated Bag of Features pooling (2022)


Laakom, F., Raitoharju, J., Iosifidis, A., & Gabbouj, M. (2022). Efficient CNN with uncorrelated Bag of Features pooling. In SSCI 2022 : Proceedings of the 2022 IEEE Symposium Series on Computational Intelligence (pp. 1082-1087). IEEE. https://doi.org/10.1109/SSCI51031.2022.10022157


JYU authors or editors


Publication details

All authors or editorsLaakom, Firas; Raitoharju, Jenni; Iosifidis, Alexandros; Gabbouj, Moncef

Parent publicationSSCI 2022 : Proceedings of the 2022 IEEE Symposium Series on Computational Intelligence

Place and date of conferenceSingapore4.-7.12.2022

ISBN978-1-6654-8769-6

eISBN978-1-6654-8768-9

Publication year2022

Publication date30/01/2023

Pages range1082-1087

PublisherIEEE

Publication countryUnited States

Publication languageEnglish

DOIhttps://doi.org/10.1109/SSCI51031.2022.10022157

Publication open accessNot open

Publication channel open access

Web address of parallel published publication (pre-print)https://arxiv.org/abs/2209.10865


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.


Keywordscomputer visionautomated pattern recognitionmachine learningdeep learningneural networks (information technology)

Free keywordsdeep learning; CNN; diversity; bag of features pooling


Contributing organizations


Related projects


Ministry reportingYes

Reporting Year2022

JUFO rating1


Last updated on 2024-03-04 at 18:46