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: extended abstract

      Wang, Hongyu; Fraser, Huon; Gouk, Henry; Frank, Eibe; Pfahringer, Bernhard; Mayo, Michael; Holmes, Geoff
      Thumbnail
      Files
      wang22a.pdf
      Published version, 188.4Kb
      Link
       proceedings.mlr.press
      Permanent link to Research Commons version
      https://hdl.handle.net/10289/15453
      Abstract
      We summarise experiments (Wang et al., 2022) evaluating cross-domain few-shot learning (CDFSL) with feature extractors trained on ImageNet. The work explores the transfer performance of extracted features on five target domains with different degrees of similarity to ImageNet. These experiments compare robust classifiers and normalisation methods, consider multi-instance learning algorithms, and evaluate the effect of using features extracted by different ResNet backbones at various levels of their convolutional hierarchies. The cosine similarity classifier and 1-vs-rest logistic regression with ℓ2 regularisation are the top-performing robust classifiers in the evaluation, and ℓ2 normalisation improves performance on all five target domains when using LDA as the robust classifier. The results also show that feature extractors with the highest capacity do not always achieve the best CDFSL performance. Lastly, simple multi-instance learning methods are shown to improve classifier accuracy.
      Date
      2022
      Type
      Conference Contribution
      Publisher
      PMLR
      Rights
      © 2022 The Authors
      Collections
      • Computing and Mathematical Sciences Papers [1455]
      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