Boosting Deep Transfer Learning for COVID-19 Classification

TL;DR

This paper introduces a novel model augmentation technique that significantly improves transfer learning accuracy for COVID-19 classification using limited chest CT data, outperforming traditional methods.

Contribution

It proposes a new augmentation strategy that reduces domain shift and combines representation learning to enhance transfer learning for COVID-19 detection.

Findings

Performance boost over vanilla transfer learning

Effective reduction of domain distributional shift

Validated on public datasets with improved accuracy

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.