Disentangling Latent Factors of Variational Auto-Encoder with Whitening
This work addresses the challenge of interpretable latent representations in generative models for researchers, though it appears incremental as it builds on existing VAE frameworks with a traditional technique.
The paper tackles the problem of learning disentangled latent variables in deep generative models, which often leads to degraded reconstruction quality or increased model complexity, by proposing a simple whitening-based method applied to VAEs that maintains reconstruction error while finding more interpretable factors.
After deep generative models were successfully applied to image generation tasks, learning disentangled latent variables of data has become a crucial part of deep generative model research. Many models have been proposed to learn an interpretable and factorized representation of latent variable by modifying their objective function or model architecture. To disentangle the latent variable, some models show lower quality of reconstructed images and others increase the model complexity which is hard to train. In this paper, we propose a simple disentangling method based on a traditional whitening process. The proposed method is applied to the latent variables of variational auto-encoder (VAE), although it can be applied to any generative models with latent variables. In experiment, we apply the proposed method to simple VAE models and experiment results confirm that our method finds more interpretable factors from the latent space while keeping the reconstruction error the same as the conventional VAE's error.