Skip to main content

Table 8 The performance of UMLF-COVID and comparison models in three-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 0.94 0.93 0.93 0.93
LeNet 0.87 0.81 0.82 0.81
Alexnet 0.9 0.89 0.88 0.89
VGG 0.83 0.72 0.72 0.72
CovXNet 0.83 0.79 0.80 0.79
CNN-LSTM 0.9 0.9 0.9 0.9
CNN-RNN 0.89 0.89 0.89 0.89
EMCNet 0.89 0.89 0.89 0.89
  1. The strategy is 3-way 10-shot
  2. Bold values are highlight our model