PAE

Reported on 4 benchmarks across 3 tasks · 1 paper · 2 SOTA

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

Medical2 results

Image GenerationonFashion-MNIST
FID· 2020-06-09
28
best: 10.3 (GLF+perceptual loss (ours))
Probabilistic Autoencoder arXiv:2006.05479
Image GenerationonCelebA 64x64
FID· 2020-06-09
49.2
best: 1.27 (DDPM-IP)
Probabilistic Autoencoder arXiv:2006.05479

Methodology1 result

Outlier DetectiononFashion-MNIST
AUROC· 2020-06-09
0.997
SOTA
Probabilistic Autoencoder arXiv:2006.05479

Computer Vision1 result

Out-of-Distribution DetectiononFashion-MNIST
AUROC· 2020-06-09
0.997
SOTA
Probabilistic Autoencoder arXiv:2006.05479