List your company
ResearchFormerly WizWand

Image Generation on CIFAR-10 (32x32, latent dim 32, test)

93.53FIDVAE - OURS
89.2032118.4091147.615176.8209Sep 15, 2022
Updated 8mo ago

Evaluation results

MethodLinks
VAE - OURSSampling=Geometry-aware2022.0993.537168
RAE (SN)Latent Prior=10-component GMM, Regularization=Spectral2022.09114.593253
RAELatent Prior=10-component GMM2022.09118.253557
RAE (GP)Latent Prior=10-component GMM, Regularization=GP2022.09120.323458
RAE (L2)Latent Prior=10-component GMM, Regularization=L22022.09123.253354
AE - GMMLatent Prior=10-component GMM2022.09130.283558
WAE2022.09132.992452
VAE - GMMLatent Prior=10-component GMM2022.09138.252953
VAE - N(0, 1)Latent Prior=N(0, 1)2022.09162.581032
RHVAE2022.09167.411222
AE - N(0, 1)Latent Prior=N(0, 1)2022.09196.5517
VAMP2022.09198.14511
HVAE2022.09201.71321