A One-Shot Learning Approach to Image Classification Using Genetic Programming

Created by W.Langdon from gp-bibliography.bib Revision:1.3973

@InProceedings{Al-Sahaf:2013:AI,
  author =       "Harith Al-Sahaf and Mengjie Zhang and Mark Johnston",
  title =        "A One-Shot Learning Approach to Image Classification
                 Using Genetic Programming",
  booktitle =    "Proceedings of the 26th Australasian Joint Conference
                 on Artificial Intelligence (AI2013)",
  year =         "2013",
  editor =       "Stephen Cranefield and Abhaya Nayak",
  volume =       "8272",
  series =       "LNAI",
  pages =        "110--122",
  address =      "Dunedin, New Zealand",
  month =        "1-6 " # dec,
  publisher =    "Springer",
  keywords =     "genetic algorithms, genetic programming, Local Binary
                 Patterns, Image Classification, One-shot Learning",
  isbn13 =       "978-3-319-03679-3",
  URL =          "http://dx.doi.org/10.1007/978-3-319-03680-9_13",
  DOI =          "doi:10.1007/978-3-319-03680-9_13",
  size =         "13 pages",
  abstract =     "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
                 Naive 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.",
}

Genetic Programming entries for Harith Al-Sahaf Mengjie Zhang Mark Johnston

Citations