Title

Boosting deep transfer learning for COVID-19 classification

Author Identifier

Syed Mohammed Shamsul Islam

ORCID : 0000-0002-3200-2903

Naeem Janjua

ORCID : 0000-0003-0483-8196

Document Type

Conference Proceeding

Publication Title

2021 IEEE International Conference on Image Processing (ICIP)

Publisher

IEEE

School

School of Science

RAS ID

36621

Funders

Australian Government

Comments

Altaf, F., Islam, S., Janjua, N. K., & Akhtar, N. (2021, September). Boosting deep transfer learning for COVID-19 classification [Paper presentation]. 2021 IEEE International Conference on Image Processing (ICIP), Anchorage, AK, USA. https://doi.org/10.1109/ICIP42928.2021.9506646

Abstract

COVID-19 classification using chest Computed Tomography (CT) has been found pragmatically useful by several studies. Due to the lack of annotated samples, these studies recommend transfer learning and explore the choices of pre-trained models and data augmentation. However, it is still unknown if there are better strategies than vanilla transfer learning for more accurate COVID-19 classification with limited CT data. This paper provides an affirmative answer, devising a novel ‘model’ augmentation technique that allows a considerable performance boost to transfer learning for the task. Our method systematically reduces the distributional shift between the source and target domains and considers augmenting deep learning with complementary representation learning techniques. We establish the efficacy of our method with publicly available datasets and models, along with identifying contrasting observations in the previous studies.

DOI

10.1109/ICIP42928.2021.9506646

Access Rights

subscription content

Research Themes

Health

Priority Areas

Multidisciplinary biological approaches to personalised disease diagnosis, prognosis and management

Share

 
COinS