The paper claims that KL-induced compactness, not stochasticity, is the key to VAE generative capability, supported by new latent-space uniformity metrics and codebook regularizer experiments.
Towards Better Data Augmentation using Wasserstein Distance in Variational Auto-encoder
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
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.
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
From Points to Spheres: A Geometric Reinterpretation of Variational Autoencoders
The paper claims that KL-induced compactness, not stochasticity, is the key to VAE generative capability, supported by new latent-space uniformity metrics and codebook regularizer experiments.