Skip to main content

Table 4 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 0.97 0.97 0.97 0.97
LeNet 0.92 0.92 0.92 0.92
Alexnet 0.91 0.89 0.89 0.89
VGG 0.85 0.83 0.83 0.83
CovXNet 0.91 0.89 0.88 0.89
CNN-LSTM 0.93 0.93 0.93 0.93
CNN-RNN 0.92 0.92 0.92 0.92
EMCNet 0.92 0.91 0.92 0.91
  1. The strategy is 3-way 10-shot
  2. Bold values are highlight our model