notesum.ai

Published at December 9

Normalizing Flows are Capable Generative Models

cs.CV

cs.LG

Released Date: December 9, 2024

Authors: Shuangfei Zhai¹, Ruixiang Zhang, Preetum Nakkiran, David Berthelot, Jiatao Gu, Huangjie Zheng, Tianrong Chen, Miguel Angel Bautista, Navdeep Jaitly, Josh Susskind

Aff.: ¹Apple

Arxiv: http://arxiv.org/pdf/2412.06329v1

Model	Type	BPD $\downarrow$
Very Deep VAE (Child, 2021)	VAE	3.52
Glow (Kingma & Dhariwal, 2018)	Flow	3.81
Flow++ (Ho et al., 2019)	Flow	3.69
PixelCNN (van den Oord et al., 2016a)	AR	3.83
SPN (Menick & Kalchbrenner, 2019)	AR	3.52
Sparse Transformer (Child et al., 2019)	AR	3.44
Routing Transformer (Roy et al., 2021)	AR	3.43
Improved DDPM (Nichol & Dhariwal, 2021)	Diff/FM	3.54
VDM (Kingma et al., 2021)	Diff/FM	3.40
Flow Matching (Lipman et al., 2023a)	Diff/FM	3.31
NFDM (Bartosh et al., 2024)	Diff/FM	3.20
TarFlow [2-768-8-8- $\mathcal{U}(0,\frac{1}{128})$ ] (Ours)	NF	2.99