Highly Efficient Representation and Active Learning Framework for Imbalanced Data and its Application to COVID-19 X-Ray Classification
Highly Efficient Representation and Active Learning Framework for Imbalanced Data and its Application to COVID-19 X-Ray Classification
Heng Hao,Sima Didari,2 Authors,P. Bangert
2021 · DBLP: journals/corr/abs-2103-05109
arXiv.org · 6 Citations
TLDR
A novel framework based on unsupervised representation learning of a Convolutional Neural Network and the Gaussian Process method for classifying chest X-rays that outperforms the state-of-the-art model with a highly tuned architecture and is less sensitive to the prevalent and challenging class imbalance issue.