מושגי ליבה
This paper argues that incorporating both mutual information and independence constraints within a generative adversarial network (GAN) framework can significantly improve the quality of disentangled representations in deep learning, leading to enhanced explainability and controllability.
סטטיסטיקה
Our method outperforms baseline methods by a considerable margin on Explicitness, Modularity and SAP scores.
We used a batch size of 64 and trained the model for 30 epochs, then selected the checkpoint with the highest Explicitness score for evaluation on other metrics.