Hang Yang

Hang Yang

he/him

PhD candidate in Mathematics at UMass Amherst. Researching machine learning, robotics, and deep learning — including mobile motion capture with robot dogs, invertible neural networks for image steganography, and vision transformers for medical AI.

CovidViT: a novel neural network with self-attention mechanism to detect Covid-19 through X-ray images

Published in International Journal of Machine Learning and Cybernetics, 2022

We propose CovidViT, a vision transformer-based neural network for detecting COVID-19 from chest X-ray images. To the best of our knowledge, this is the first application of the transformer architecture and self-attention mechanism to COVID-19 detection.

The model classifies chest X-rays into three categories: normal, COVID-19, and viral pneumonia. Experimental results show CovidViT achieves 98.0% accuracy on the test set, outperforming other state-of-the-art deep learning models.

Hang Yang and Liyang Wang contributed equally to this work. The work was conducted at the College of Science, China Agricultural University, Beijing, China.

Recommended citation: Yang, H., Wang, L., Xu, Y., et al. (2023). "CovidViT: a novel neural network with self-attention mechanism to detect Covid-19 through X-ray images." International Journal of Machine Learning and Cybernetics, 14, 973–987.
Download Paper