AustralasianAI.pdf (967.69 kB)

A One-shot Learning Approach to Image Classification using Genetic Programming

Download (967.69 kB)
conference contribution
posted on 27.10.2020, 21:39 by Harith Al-Sahaf, Mengjie Zhang, M Johnston
In machine learning, it is common to require a large number of instances to train a model for classification. In many cases, it is hard or expensive to acquire a large number of instances. In this paper, we propose a novel genetic programming (GP) based method to the problem of automatic image classification via adopting a one-shot learning approach. The proposed method relies on the combination of GP and Local Binary Patterns (LBP) techniques to detect a predefined number of informative regions that aim at maximising the between-class scatter and minimising the within-class scatter. Moreover, the proposed method uses only two instances of each class to evolve a classifier. To test the effectiveness of the proposed method, four different texture data sets are used and the performance is compared against two other GP-based methods namely Conventional GP and Two-tier GP. The experiments revealed that the proposed method outperforms these two methods on all the data sets. Moreover, a better performance has been achieved by Naïve Bayes, Support Vector Machine, and Decision Trees (J48) methods when extracted features by the proposed method have been used compared to the use of domain-specific and Two-tier GP extracted features. © Springer International Publishing 2013.

History

Preferred citation

Al-Sahaf, H., Zhang, M. & Johnston, M. (2013, January). A One-shot Learning Approach to Image Classification using Genetic Programming. In AI 2013: Advances in Artificial Intelligence 26th Australasian Joint Conference Dunedin, New Zealand, December 1-6, 2013 Proceedings AI 2013: Advances in Artificial Intelligence 26th Australasian Joint Conference Dunedin, New Zealand, December 1-6, 2013, Dunedin (8272 LNAI pp. 110-122). Berlin: Springer. https://doi.org/10.1007/978-3-319-03680-9

Conference name

AI 2013: Advances in Artificial Intelligence 26th Australasian Joint Conference Dunedin, New Zealand, December 1-6, 2013

Conference Place

Dunedin

Conference start date

01/12/2013

Conference finish date

06/12/2013

Title of proceedings

AI 2013: Advances in Artificial Intelligence 26th Australasian Joint Conference Dunedin, New Zealand, December 1-6, 2013 Proceedings

Volume

8272 LNAI

Contribution type

Published Paper

Publication or Presentation Year

01/01/2013

Pagination

110-122

Publisher

Springer

Publication status

Published

ISSN

0302-9743

eISSN

1611-3349

Place of publication

Berlin

Exports

Logo branding

Categories

Exports