TEVC3.pdf (3.49 MB)

Cross-Domain Reuse of Extracted Knowledge in Genetic Programming for Image Classification

Download (3.49 MB)
journal contribution
posted on 28.10.2020, 04:38 by M Iqbal, Bing Xue, Harith Al-Sahaf, Mengjie Zhang
© 2017 IEEE. Genetic programming (GP) is a well-known evolutionary computation technique, which has been successfully used to solve various problems, such as optimization, image analysis, and classification. Transfer learning is a type of machine learning approach that can be used to solve complex tasks. Transfer learning has been introduced to GP to solve complex Boolean and symbolic regression problems with some promise. However, the use of transfer learning with GP has not been investigated to address complex image classification tasks with noise and rotations, where GP cannot achieve satisfactory performance, but GP with transfer learning may improve the performance. In this paper, we propose a novel approach based on transfer learning and GP to solve complex image classification problems by extracting and reusing blocks of knowledge/information, which are automatically discovered from similar as well as different image classification tasks during the evolutionary process. The proposed approach is evaluated on three texture data sets and three office data sets of image classification benchmarks, and achieves better classification performance than the state-of-the-art image classification algorithm. Further analysis on the evolved solutions/trees shows that the proposed approach with transfer learning can successfully discover and reuse knowledge/information extracted from similar or different problems to improve its performance on complex image classification problems.

Funding

Large-scale Evolutionary Feature Selection for Classification | Funder: Royal Society of New Zealand | Grant ID: 16-VUW-111

History

Preferred citation

Iqbal, M., Xue, B., Al-Sahaf, H. & Zhang, M. (2017). Cross-Domain Reuse of Extracted Knowledge in Genetic Programming for Image Classification. IEEE Transactions on Evolutionary Computation, 21(4), 569-587. https://doi.org/10.1109/TEVC.2017.2657556

Journal title

IEEE Transactions on Evolutionary Computation

Volume

21

Issue

4

Publication date

01/08/2017

Pagination

569-587

Publisher

IEEE

Publication status

Published

Contribution type

Article

Online publication date

25/01/2017

ISSN

1089-778X

eISSN

1941-0026

Language

en

Exports