MaCow: Masked Convolutional Generative Flow

By Xuezhe Ma, Eduard H. Hovy. 2019

69 citations recorded by the source corpus.

Flow-based generative models, conceptually attractive due to tractability of both the exact log-likelihood computation and latent-variable inference, and efficiency of both training and sampling, has led to a number of impressive empirical successes and spawned many advanced variants and theoretical investigations. Despite their computational efficiency, the density estimation performance of flow-based generative models significantly falls behind those of state-of-the-art autoregressive models. In this work, we introduce masked convolutional generative flow (MaCow), a simple yet effective architecture of generative flow using masked convolution. By restricting the local connectivity in a small kernel, MaCow enjoys the properties of fast and stable training, and efficient sampling, while achieving significant improvements over Glow for density estimation on standard image benchmarks, considerably narrowing the gap to autoregressive models.

Subfields: Computer Vision and Pattern Recognition, Statistical and Nonlinear Physics, Generative Models, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Statistical and Nonlinear Physics

In Generative Models

In Signal Processing

Citations in the corpus

NVAE: A Deep Hierarchical Variational Autoencoder (2020, methodology): “(f)-(g) A few images generated by MaCow [67] and Glow [62] are shown for comparison (images are from the original publications).”
Normalizing Flows for Probabilistic Modeling and Inference (2019, background): “Examples of flow-based models that use masking include IAF (Kingma et al., 2016), MAF (Papamakarios et al., 2017), NAF (Huang et al., 2018), B-NAF (De Cao et al., 2019), masked invertible network (MintNet) (Song et al., 2019) and masked convolutional generative flow (MaCow) (Ma et al., 2019).”
Augmented Normalizing Flows: Bridging the Gap Between Generative Flows and Latent Variable Models (2020, background): “…kernels can also be designed to to ensure tractability, such as via using 1 × 1 convolution (Kingma & Dhariwal, 2018), masking (Oord et al., 2016; van den Oord et al., 2016; Hoogeboom et al., 2019; Song et al., 2019; Ma et al., 2019) or imposing certain repeated structure (Karami et al., 2019).”
MintNet: Building Invertible Neural Networks with Masked Convolutions (2019, methodology): “Emerging convolutions [13] and MaCow [20] improve the Glow architecture by replacing 1 × 1 convolutions in the original Glow model with masked convolutions similar to those employed in MintNets.”
FlowSeq: Non-Autoregressive Conditional Sequence Generation with Generative Flow (2019, background): “This framework can elegantly model complex distributions, and has obtained remarkable success in modeling continuous data such as images and speech through efﬁcient density estimation and sampling (Kingma and Dhariwal, 2018; Prenger et al., 2019; Ma and Hovy, 2019).”
Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Models (2021, background): “A number of these apply variations on causal convolutions [229], including emerging convolutions [90] whose inverse is sequential, MaCow [144] which uses smaller conditional fields allowing more efficient sampling, and MintNet [203] which approximates the inverse using fixedpoint iteration.”
Efficient-VDVAE: Less is more (2022, methodology): “In table 4, we test the effect of this removal on FFHQ 256× 256 and CelebAHQ 256× 256 which have been consistently quantized to 5-bits in prior work [16, 23, 47, 48, 38, 37, 32, 39, 34].”
Why Normalizing Flows Fail to Detect Out-of-Distribution Data (2020, background): “…and allows for eﬃcient Jacobian computation in (1): Flows with coupling layers Coupling layers can be stacked together into ﬂexible normalizing ﬂows: ◦ ◦ ◦ Examples of ﬂows with coupling layers include NICE [9], RealNVP [10], Glow [22], and many others [e.g., 4, 5, 11, 15, 16, 21, 25, 32].”
Wavelet Flow: Fast Training of High Resolution Normalizing Flows (2020, background): “, [24, 31]) have instead shown samples drawn from an annealed version of the estimated distribution.”