Flow++

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 64x64
Bits per dim· 2019-02-01
3.69
best: 4.351 (Logsparse (6 layers))
Flow++: Improving Flow-Based Generative Models with Variational Dequantization and Architecture Design arXiv:1902.00275
Image GenerationonImageNet 32x32
bpd· 2019-02-01
3.86
best: 3.34 (NFDM)
Flow++: Improving Flow-Based Generative Models with Variational Dequantization and Architecture Design arXiv:1902.00275