CoVAE trains a time-dependent VAE with a consistency loss so one or few decoder passes generate images, reaching FID 5.62 on MNIST and 11.69 on CIFAR-10 with adversarial loss, without a learned prior.
Representation learning: A review and new perspectives
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
CoVAE: Consistency Training of Variational Autoencoders
CoVAE trains a time-dependent VAE with a consistency loss so one or few decoder passes generate images, reaching FID 5.62 on MNIST and 11.69 on CIFAR-10 with adversarial loss, without a learned prior.