TensorFlow implementation of Disentangled Generative Model (DGM) with MNIST dataset.
The objective functions (losses) for training DGM [1].
The architecture of DGM.
Graph of DGM.
'Class-1' is defined as normal and the others are defined as abnormal.
Losses for training generative components.Each graph shows adversarial loss, reconstruction loss, and total variation loss sequentially.
Loss graphs in the training procedure.Each graph shows generative loss and discriminative loss respectively.
Restoration result by DGM.
Box plot with encoding loss of test procedure.
Normal samples classified as normal.
Abnormal samples classified as normal.
Normal samples classified as abnormal.
Abnormal samples classified as abnormal.
[1] Youbao Tang et al. (2021). A disentangled generative model for disease decomposition in chest X-rays via normal image synthesis. Medical Image Analysis. ELSEVIER.