AI Paper Atlas

Research map / Probabilistic and scientific modeling / Variational and generative sampling

MaCow: Masked Convolutional Generative Flow

Xuezhe Ma, Xiang Kong, Shanghang Zhang, Eduard Hovy

NeurIPS 2019 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Expressive invertible architectures · 5 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add fine-grained multi-scale architecture to MaCow (ablation)MaCow · CIFAR-10bits/dim: 3.31 -> 3.28Improved
add fine-grained multi-scale architecture to MaCow (ablation)MaCow · ImageNet 64x64bits/dim: 3.78 -> 3.75Improved
add variational dequantization to MaCow (ablation)MaCow +fine-grained · CIFAR-10bits/dim: 3.28 -> 3.16Improved
add variational dequantization to MaCow (ablation)MaCow +fine-grained · ImageNet 64x64bits/dim: 3.75 -> 3.69Improved
replace Glow with MaCow (uniform dequantization)Glow · CIFAR-10bits/dim: 3.35 -> 3.28Improved
replace Glow with MaCow (uniform dequantization)Glow · ImageNet 64x64bits/dim: 3.81 -> 3.75Improved
MaCow with variational dequantization vs Flow++ VarMaCow · CIFAR-10bits/dim: 3.09 -> 3.16Hurt
MaCow with variational dequantization vs Flow++ VarMaCow · ImageNet 64x64bits/dim: 3.69 -> 3.69No clear effect
variational instead of uniform dequantization (ablation)MaCow · CelebA-HQbits/dim: 0.95 -> 0.67Improved
variational instead of uniform dequantization (ablation)MaCow · LSUN bedroombits/dim: 1.16 -> 0.98Improved
variational instead of uniform dequantization (ablation)MaCow · LSUN towerbits/dim: 1.22 -> 1.02Improved
variational instead of uniform dequantization (ablation)MaCow · LSUN churchbits/dim: 1.36 -> 1.09Improved

Later papers that compared with this method

2 later accepted papers report MACow as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 3 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy