A Study on CNN Transfer Learning for Image Classification

Mahbub Hussain, Jordan J. Bird, Diego R. Faria

Research output: Chapter in Book/Published conference outputConference publication


Many image classification models have been introduced to help tackle the foremost issue of recognition accuracy. Image classification is one of the core problems in Computer Vision field with a large variety of practical applications. Examples include: object recognition for robotic manipulation, pedestrian or obstacle detection for autonomous vehicles, among others. A lot of attention has been associated with Machine Learning, specifically neural networks such as the Convolutional Neural Network (CNN) winning image classification competitions. This work proposes the study and investigation of such a CNN architecture model (i.e. Inception-v3) to establish whether it would work best in terms of accuracy and efficiency with new image datasets via Transfer Learning. The retrained model is evaluated, and the results are compared to some state-of-the-art approaches.
Original languageEnglish
Title of host publicationUK Workshop on Computational Intelligence
Place of Publication840
ISBN (Electronic)978-3-319-97982-3
ISBN (Print)978-3-319-97981-6
Publication statusE-pub ahead of print - 11 Aug 2018
EventUKCI'18: 18th Annual UK Workshop on Computational Intelligence - Nottingham, United Kingdom
Duration: 5 Sept 20187 Sept 2018

Publication series

NameAdvances in Computational Intelligence Systems
ISSN (Print)2194-5357
ISSN (Electronic)2194-5365


ConferenceUKCI'18: 18th Annual UK Workshop on Computational Intelligence
Country/TerritoryUnited Kingdom


Dive into the research topics of 'A Study on CNN Transfer Learning for Image Classification'. Together they form a unique fingerprint.

Cite this