ANF Huang et al. (2020)

Reported on 2 benchmarks across 1 task · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Medical2 results

Image GenerationonImageNet 32x32
bpd· 2020-02-17
3.92
best: 3.34 (NFDM)
Augmented Normalizing Flows: Bridging the Gap Between Generative Flows and Latent Variable Models arXiv:2002.07101
Image GenerationonCelebA 256x256
bpd· 2020-02-17
0.72
best: 0.51 (Efficient-VDVAE)
Augmented Normalizing Flows: Bridging the Gap Between Generative Flows and Latent Variable Models arXiv:2002.07101