Towards Better Data Augmentation using Wasserstein Distance in Variational Auto-encoder
This work addresses data augmentation challenges for machine learning practitioners, but it is incremental as it modifies an existing method.
The paper tackled the problem of improving data augmentation in variational auto-encoders by replacing KL divergence with Wasserstein distance for latent attribute similarity, resulting in better convergence and enhanced artificial image generation for image classification tasks.
VAE, or variational auto-encoder, compresses data into latent attributes, and generates new data of different varieties. VAE based on KL divergence has been considered as an effective technique for data augmentation. In this paper, we propose the use of Wasserstein distance as a measure of distributional similarity for the latent attributes, and show its superior theoretical lower bound (ELBO) compared with that of KL divergence under mild conditions. Using multiple experiments, we demonstrate that the new loss function exhibits better convergence property and generates artificial images that could better aid the image classification tasks.