Loughborough University
Browse
IEEE Conference paper v2.pdf (542.18 kB)

A model selection algorithm for complex CNN systems based on feature-weights relation

Download (542.18 kB)
conference contribution
posted on 2023-06-15, 13:46 authored by Eyad Alsaghir, Xiyu ShiXiyu Shi, Varuna De-SilvaVaruna De-Silva

In object recognition using machine learning, one model cannot practically be trained to identify all the possible objects it encounters. An ensemble of models may be needed to cater to a broader range of objects. Building a mathematical understanding of the relationship between various objects that share comparable outlined features is envisaged as an effective method of improving the model ensemble through a pre-processing stage, where these objects' features are grouped under a broader classification umbrella. This paper proposes a mechanism to train an ensemble of recognition models coupled with a model selection scheme to scale-up object recognition in a multi-model system. The multiple models are built with a CNN structure, whereas the image features are extracted using a CNN/VGG16 architecture. Based on the models' excitation weights, a neural network model selection algorithm, which decides how close the features of the object are to the trained models for selecting a particular model for object recognition is tested on a multi-model neural network platform. The experiment results show the proposed model selection scheme is highly effective and accurate in selecting an appropriate model for a network of multiple models.

History

School

  • Loughborough University London

Published in

2023 IEEE IAS Global Conference on Emerging Technologies (GlobConET)

Source

2023 IEEE IAS Global Conference on Emerging Technologies

Publisher

IEEE

Version

  • AM (Accepted Manuscript)

Rights holder

© IEEE

Publisher statement

© 2023 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

Acceptance date

2023-03-19

Publication date

2023-06-16

Copyright date

2023

ISBN

9798350331790

Language

  • en

Location

London, UK

Event dates

19th May 2023 - 21st May 2023

Depositor

Dr Xiyu Shi. Deposit date: 15 June 2023

Usage metrics

    Loughborough Publications

    Categories

    No categories selected

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC