Genetic programming with transfer learning for texture image classification
- 194 Downloads
Genetic programming (GP) represents a well-known and widely used evolutionary computation technique that has shown promising results in optimisation, classification, and symbolic regression problems. However, similar to many other techniques, the performance of GP deteriorates for solving highly complex tasks. Transfer learning can improve the learning ability of GP, which can be seen from previous research on including, but not limited to, symbolic regression and Boolean problems. However, utilising transfer learning to tackle image-related, specifically, image classification, problems in GP is limited. This paper aims at proposing a new method for employing transfer learning in GP to extract and transfer knowledge in order to tackle complex texture image classification problems. To assess the improvement gained from using the extracted knowledge, the proposed method is examined and compared against the baseline GP method and a state-of-the-art method on three publicly available and commonly used texture image classification datasets. The obtained results indicate that the reuse of the extracted knowledge from an image dataset has significant impact on improving the performance in learning different rotated versions of the same dataset, as well as other related image datasets. Further, it is found that the proposed approach in the very first generation of the evolutionary process produces better classification accuracy than the final classification accuracy obtained by the baseline method after 50 generations.
KeywordsGenetic programming Transfer learning Image classification Code fragments Evolutionary computation
This work is supported in part by the Marsden Fund (Contract Numbers VUW1509, VUW1615) of New Zealand, and the University research grant of Victoria University of Wellington (Grant Numbers 213150 and 216137). Bing Xue received research grants from Marsden Fund (VUW1615) of New Zealand and from Victoria University of Wellington (213150). Mengjie Zhang received the research grants from Marsden Fund of New Zealand (VUW1509) and Victoria University of Wellington (216137).
Compliance with ethical standards
Conflicts of interest
The authors declare that they have no conflict of interest.
This article does not contain any studies with human participants or animals performed by any of the authors.
- Al-Sahaf H, Zhang M, Johnston M, Verma B (2015)Image descriptor: a genetic programming approach to multiclass texture classification. In: Proceedings of 2015 IEEE congress on evolutionary computation. IEEE, pp 2460–2467Google Scholar
- Al-Sahaf H, Al-Sahaf A, Xue B, Johnston M, Zhang M (2017) Automatically evolving rotation-invariant texture image descriptors by genetic programming. IEEE Trans Evol Comput 21(1):83–101Google Scholar
- Blanchard G, Lee G, Scott C (2011) Generalizing from several related classification tasks to a new unlabeled sample. In: Proceedings of 2011 advances in neural information processing systems. Curran Associates, pp 2178–2186Google Scholar
- Blitzer J, McDonald R, Pereira F (2006) Domain adaptation with structural correspondence learning. In: Proceedings of the 2006 conference on empirical methods in natural language processing. Association for Computational Linguistics, pp 120–128Google Scholar
- Brodatz P (1999) Textures: a photographic album for artists and designers. Dover Publications, New YorkGoogle Scholar
- Chen Q, Xue B, Zhang M (2015) Generalisation and domain adaptation in GP with gradient descent for symbolic regression. In: Proceedings of 2015 IEEE Congress on Evolutionary Computation. IEEE, pp 1137–1144Google Scholar
- Donahue J, Jia Y, Vinyals O, Hoffman J, Zhang N, Tzeng E, Darrell T (2014) DeCAF: a deep convolutional activation feature for generic visual recognition. In: Proceedings of the 31st international conference in machine learning, international conference on machine learning, vol 32. PMLR, pp 647–655Google Scholar
- Fogel DB (2007) Introduction to evolutionary computation, chap 1. Wiley, New York, pp 1–23Google Scholar
- Ghifary M, Kleijn WB, Zhang M (2014) Domain adaptive neural networks for object recognition. In: Proceedings of the 13th Pacific Rim international conference on artificial intelligence. Springer, pp 898–904Google Scholar
- Ghifary M, Kleijn WB, Zhang M, Balduzzi D (2015) Domain generalization for object recognition with multi-task autoencoders. In: Proceedings of 2015 IEEE international conference on computer vision. IEEE, pp 2551–2559Google Scholar
- Hafemann LG, Oliveira LS, Cavalin PR, Sabourin R (2015) Transfer learning between texture classification tasks using convolutional neural networks. In: Proceedings of the 2015 international joint conference on neural networks. IEEE, pp 1–7Google Scholar
- Hien NT, Hoai NX, McKay B (2011) A study on genetic programming with layered learning and incremental sampling. In: Proceedings of 2011 IEEE congress on evolutionary computation. IEEE, pp 1179–1185Google Scholar
- Iqbal M, Xue B, Zhang M (2016a) Reusing extracted knowledge in genetic programming to solve complex texture image classification problems. In: Proceedings of the 20th Pacific Asia knowledge discovery and data mining conference, Part II. Springer, pp 117–129Google Scholar
- Iqbal M, Zhang M, Xue B (2016b) Improving classification on images by extracting and transferring knowledge in genetic programming. In: Proceedings of 2016 IEEE congress on evolutionary computation. IEEE, pp 3582–3589Google Scholar
- Jackson D, Gibbons AP (2007) Layered learning in boolean GP problems. In: Proceedings of the European conference on genetic programming, lecture notes in computer science, vol 4445. Springer, pp 148–159Google Scholar
- Kylberg G (2011) The Kylberg texture dataset v. 1.0. External report (Blue series) 35, centre for image analysis, Swedish University of Agricultural Sciences and Uppsala University, Uppsala, SwedenGoogle Scholar
- Lensen A, Al-Sahaf H, Zhang M, Xue B (2015) A hybrid genetic programming approach to feature detection and image classification. In: Proceedings of the 30th international conference on image and vision computing New Zealand. IEEE, pp 1–6Google Scholar
- Lensen A, Al-Sahaf H, Zhang M, Xue B (2016) Genetic programming for region detection, feature extraction, feature construction and classification in image data. In Proceedings of the 19th European conference on genetic programming, lecture notes in computer science, vol 9594. Springer, pp 49–64Google Scholar
- Li Y, Ma J, Zhao Q (2008) Two improvements in genetic programming for image classification. In: Proceedings of the IEEE congress on evolutionary computation, pp 2492–2497Google Scholar
- Luke S (2013) Essentials of metaheuristics, 2nd edn. Lulu. https://cs.gmu.edu/~sean/book/metaheuristics/
- Muandet K, Balduzzi D, Schölkopf B (2013) Domain generalization via invariant feature representation. In: Proceedings of the international conference on machine learning, pp 10–18. JMLR.orgGoogle Scholar
- Ojala T, Mäenpää T, Pietikäinen M, Viertola J, Kyllonen J, Huovinen S (2002) Outex—new framework for empirical evaluation of texture analysis algorithms. In: Proceedings of the 16th international conference on pattern recognition, vol 1. IEEE, pp 701–706Google Scholar
- Perez CB, Olague G (2009) Evolutionary learning of local descriptor operators for object recognition. In: Proceedings of the 11th annual conference on genetic and evolutionary computation. ACM, pp 1051–1058Google Scholar
- Poli R, Langdon WB, McPhee NF (2008) A field guide to genetic programming (with contributions by Koza JR). http://www.gp-field-guide.org.uk/