Flow++: Improving Flow-Based Generative Models with Variational Dequantization and Architecture Design

Flow-based generative models are powerful exact likelihood models with efficient sampling and inference. Despite their computational efficiency, flow-based models generally have much worse density modeling performance compared to state-of-the-art autoregressive models... (read more)

PDF Abstract ICLR 2019 PDF ICLR 2019 Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Image Generation CIFAR-10 Flow++ bits/dimension 3.08 # 13
Image Generation ImageNet 32x32 Flow++ bpd 3.86 # 5
Image Generation ImageNet 64x64 Flow++ Bits per dim 3.69 # 5

Methods used in the Paper


METHOD TYPE
🤖 No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet