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.

      Experiments in cross-domain few-shot learning for image classification

      Wang, Hongyu; Gouk, Henry; Fraser, Huon; Frank, Eibe; Pfahringer, Bernhard; Mayo, Michael; Holmes, Geoffrey
      Files
      experiments_in_cdfsl_for_image_classification.pdf
      Accepted version, 1.602Mb
      This file wil be publicly accessible from 2023-04-23
      Request a copy
      DOI
       10.1080/03036758.2022.2059767
      Find in your library  
      Permanent link to Research Commons version
      https://hdl.handle.net/10289/14832
      Abstract
      Cross-domain few-shot learning has many practical applications. This paper attempts to shed light on suitable configurations of feature exactors and ‘shallow’ classifiers in this machine learning setting. We apply ResNet-based feature extractors pretrained on two versions of the ImageNet dataset to five target domains with different degrees of similarity to ImageNet, varying the feature extractor size, the network stage at which features are extracted, and the learning algorithm applied to the extracted features. We evaluate standard learning algorithms such as logistic regression and linear discriminant analysis, as well as variants thereof, and additionally consider the effect of normalising the feature vectors using various p-norms. We also apply multi-instance learning to improve training image utilisation. In our experiments, the cosine similarity classifier and ℓ2-regularised 1-vs-rest logistic regression generally exhibit the best classification performance. We also find that algorithms such as linear discriminant analysis yield consistently higher accuracy using ℓ2-normalised feature vectors. Features extracted from the penultimate stage of a ResNet-101 model, and multi-instance learning techniques, produce the highest accuracy for most target domains. Our results will inform practitioners who are considering the application of pretrained ImageNet feature extractors in cross-domain few-shot settings.
      Date
      2022
      Type
      Journal Article
      Publisher
      Informa UK Limited
      Rights
      This is an Accepted Manuscript of an article published by Taylor & Francis in Journal of the Royal Society of New Zealand on April 22, 2022, available at: http://www.tandfonline.com/10.1080/03036758.2022.2059767
      Collections
      • Computing and Mathematical Sciences Papers [1431]
      Show full item record  

      Usage

       
       
       

      Usage Statistics

      For this itemFor all of Research Commons

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