Research Commons
      • Browse 
        • Communities & Collections
        • Titles
        • Authors
        • By Issue Date
        • Subjects
        • Types
        • Series
      • Help 
        • About
        • Collection Policy
        • OA Mandate Guidelines
        • Guidelines FAQ
        • Contact Us
      • My Account 
        • Sign In
        • Register
      View Item 
      •   Research Commons
      • University of Waikato Research
      • Computing and Mathematical Sciences
      • Computing and Mathematical Sciences Papers
      • View Item
      •   Research Commons
      • University of Waikato Research
      • Computing and Mathematical Sciences
      • Computing and Mathematical Sciences Papers
      • View Item
      JavaScript is disabled for your browser. Some features of this site may not work without it.

      A comparison of machine learning methods for cross-domain few-shot learning

      Wang, Hongyu; Gouk, Henry; Frank, Eibe; Pfahringer, Bernhard; Mayo, Michael
      Thumbnail
      Files
      AJCAI.pdf
      Accepted version, 375.3Kb
      DOI
       10.1007/978-3-030-64984-5_35
      Find in your library  
      Citation
      Export citation
      Wang, H., Gouk, H., Frank, E., Pfahringer, B., & Mayo, M. (2020). A comparison of machine learning methods for cross-domain few-shot learning. In M. Gallagher, N. Moustafa, & E. Lakshika (Eds.), AI 2020: Advances in Artificial Intelligence. AI 2020. Lecture Notes in Computer Science (Vol. LNAI 12576, pp. 445–457). Cham, Switzerland: Springer. https://doi.org/10.1007/978-3-030-64984-5_35
      Permanent Research Commons link: https://hdl.handle.net/10289/14027
      Abstract
      We present an empirical evaluation of machine learning algorithms in cross-domain few-shot learning based on a fixed pre-trained feature extractor. Experiments were performed in five target domains (CropDisease, EuroSAT, Food101, ISIC and ChestX) and using two feature extractors: a ResNet10 model trained on a subset of ImageNet known as miniImageNet and a ResNet152 model trained on the ILSVRC 2012 subset of ImageNet. Commonly used machine learning algorithms including logistic regression, support vector machines, random forests, nearest neighbour classification, naïve Bayes, and linear and quadratic discriminant analysis were evaluated on the extracted feature vectors. We also evaluated classification accuracy when subjecting the feature vectors to normalisation using p-norms. Algorithms originally developed for the classification of gene expression data—the nearest shrunken centroid algorithm and LDA ensembles obtained with random projections—were also included in the experiments, in addition to a cosine similarity classifier that has recently proved popular in few-shot learning. The results enable us to identify algorithms, normalisation methods and pre-trained feature extractors that perform well in cross-domain few-shot learning. We show that the cosine similarity classifier and ℓ² -regularised 1-vs-rest logistic regression are generally the best-performing algorithms. We also show that algorithms such as LDA yield consistently higher accuracy when applied to ℓ² -normalised feature vectors. In addition, all classifiers generally perform better when extracting feature vectors using the ResNet152 model instead of the ResNet10 model.
      Date
      2020
      Type
      Conference Contribution
      Publisher
      Springer
      Rights
      © 2020 Springer Nature Switzerland AG. This is the author's accepted version. The final publication is available at Springer via dx.doi.org/10.1007/978-3-030-64984-5_35
      Collections
      • Computing and Mathematical Sciences Papers [1436]
      Show full item record  

      Usage

      Downloads, last 12 months
      43
       
       
       

      Usage Statistics

      For this itemFor all of Research Commons

      The University of Waikato - Te Whare Wānanga o WaikatoFeedback and RequestsCopyright and Legal Statement