Domain Generalization in Biosignal Classification.

Journal: IEEE transactions on bio-medical engineering
Published Date:

Abstract

OBJECTIVE: When training machine learning models, we often assume that the training data and evaluation data are sampled from the same distribution. However, this assumption is violated when the model is evaluated on another unseen but similar database, even if that database contains the same classes. This problem is caused by domain-shift and can be solved using two approaches: domain adaptation and domain generalization. Simply, domain adaptation methods can access data from unseen domains during training; whereas in domain generalization, the unseen data is not available during training. Hence, domain generalization concerns models that perform well on inaccessible, domain-shifted data.

Authors

  • Theekshana Dissanayake
    Department of Computer Engineering, University of Peradeniya, Peradeniya 20400, Sri Lanka. theekshanadis@eng.pdn.ac.lk.
  • Tharindu Fernando
    The Speech, Audio, Image and Video Technologies (SAIVT) research group, School of Electrical Engineering & Computer Science, Queensland University of Technology, Australia.
  • Simon Denman
    The Speech, Audio, Image and Video Technologies (SAIVT) research group, School of Electrical Engineering & Computer Science, Queensland University of Technology, Australia.
  • Houman Ghaemmaghami
  • Sridha Sridharan
    The Speech, Audio, Image and Video Technologies (SAIVT) research group, School of Electrical Engineering & Computer Science, Queensland University of Technology, Australia.
  • Clinton Fookes
    The Speech, Audio, Image and Video Technologies (SAIVT) research group, School of Electrical Engineering & Computer Science, Queensland University of Technology, Australia.