Skip to main content

Table 9 The performance of UMLF-COVID and comparison models in four-classification tasks

From: UMLF-COVID: an unsupervised meta-learning model specifically designed to identify X-ray images of COVID-19 patients

Model Precision Recall F1-score Accuracy
UMLF-COVID 0.91 0.9 0.9 0.9
LeNet 0.77 0.77 0.77 0.77
Alexnet 0.78 0.78 0.78 0.78
VGG 0.74 0.73 0.68 0.73
CovXNet 0.74 0.73 0.72 0.73
CNN-LSTM 0.8 0.8 0.8 0.8
CNN-RNN 0.79 0.79 0.79 0.79
EMCNet 0.83 0.79 0.81 0.8
  1. The strategy is 4-way 10-shot
  2. Bold values are highlight our model