Distributed Information Integration in Convolutional Neural Networks

Dinesh Kumar., Dharmendra Sharma.

Research output: A Conference proceeding or a Chapter in BookConference contribution

Abstract

A large body of physiological findings has suggested the vision system understands a scene in terms of its local features such as lines and curves. A highly notable computer algorithm developed that models such behaviour is the Convolutional Neural Network (CNN). Whilst recognising an object in various scales remains trivial for the human vision system, CNNs struggle to achieve the same behaviour. Recent physiological findings are suggesting two new paradigms. Firstly, the visual system uses both local and global features in its recognition function. Secondly, the brain uses a distributed processing architecture to learn information from multiple modalities. In this paper we combine these paradigms and propose a distributed information integration model called D-Net to improve scale-invariant classification of images. We use a CNN to extract local features and, inspired by Google’s INCEPTION model, develop a trainable method using filter pyramids to extract global features called Filt er Pyramid Convolutions (FPC). D-Net locally processes CNN and FPC features, fuses the outcomes and obtains a global estimate via the central processor. We test D-Net on classification of scaled images on benchmark datasets. Our results show D-Net’s potential effectiveness towards classification of scaled images
Original languageEnglish
Title of host publicationVISIGRAPP 2020 - Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications
EditorsGiovanni Maria Farinella, Petia Radeva, Jose Braz
Place of PublicationNetherlands
PublisherScitepress
Pages491-498
Number of pages8
Volume5
ISBN (Electronic)9789897584022
ISBN (Print)9789897584022
DOIs
Publication statusPublished - 2020
Event15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Valletta, Valletta, Malta
Duration: 27 Feb 202029 Feb 2020
http://www.visapp.visigrapp.org/?y=2020

Publication series

NameVISIGRAPP 2020 - Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications
Volume5

Conference

Conference15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications
Abbreviated titleVISAPP 2020
CountryMalta
CityValletta
Period27/02/2029/02/20
Internet address

Fingerprint Dive into the research topics of 'Distributed Information Integration in Convolutional Neural Networks'. Together they form a unique fingerprint.

  • Cite this

    Kumar., D., & Sharma., D. (2020). Distributed Information Integration in Convolutional Neural Networks. In G. M. Farinella, P. Radeva, & J. Braz (Eds.), VISIGRAPP 2020 - Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (Vol. 5, pp. 491-498). (VISIGRAPP 2020 - Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications; Vol. 5). Scitepress. https://doi.org/10.5220/0009150404910498, https://doi.org/10.5220/0009150404910498