Learning Interpretable Disentangled Representations using Adversarial VAEs

04/17/2019
by   Mhd Hasan Sarhan, et al.
0

Learning Interpretable representation in medical applications is becoming essential for adopting data-driven models into clinical practice. It has been recently shown that learning a disentangled feature representation is important for a more compact and explainable representation of the data. In this paper, we introduce a novel adversarial variational autoencoder with a total correlation constraint to enforce independence on the latent representation while preserving the reconstruction fidelity. Our proposed method is validated on a publicly available dataset showing that the learned disentangled representation is not only interpretable, but also superior to the state-of-the-art methods. We report a relative improvement of 81.50 of disentanglement, 11.60 with a few amounts of labeled data.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset