AI Paper Atlas

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

Generative Flows With Invertible Attentions

Rhea Sanjay Sukthanker, Zhiwu Huang, Suryansh Kumar, Radu Timofte, Luc Van Gool

CVPR 2022 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Expressive invertible architectures · 9 citations (OpenAlex)

This paper tried a common change: More attention heads

Use more than 5 iTrans attention heads · CIFAR10 · bits/dim No clear effect

What 107 accepted papers report for this change

See this change in detailMatched by the wording of each paper's own result, read by AI from the full text. Papers report gains more often than failures, so this shows what gets published, not the chance a change works.

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 iMap attention to mARFlowmARFlow · MNISTbits/dim: 0.56 -> 0.39Improved
Add iMap attention to mARFlowmARFlow · CIFAR10bits/dim: 3.24 -> 3.216Improved
Add iMap attention to mARFlowmARFlow · CIFAR10FID: 41.9 -> 33.6Improved
Add iTrans attention to mARFlowmARFlow · CIFAR10bits/dim: 3.24 -> 3.217Improved
Add iMap attention to SRFlowSRFlow · CelebA 8× SRSSIM: 0.73 -> 0.74Improved
Add iTrans attention to SRFlowSRFlow · CelebA 8× SRLPIPS: 0.17 -> 0.16Improved
Add iMap attention to Full-GlowFull-Glow · Cityscapes label→photoconditional bits/dim: 2.345 -> 2.310Improved
Add iTrans attention to Full-GlowFull-Glow · Cityscapes label→photoconditional bits/dim: 2.345 -> 2.314Improved
Replace spatial-channel checkerboard mask with spatial-only mask (ablation)AttnFlow-iMap · MNISTbits/dim: 0.39 -> 0.99Hurt
Replace spatial-channel checkerboard mask with channel-wise mask (ablation)AttnFlow-iMap · MNISTbits/dim: 0.39 -> 0.75Hurt
Replace spatial-channel checkerboard mask with random binary mask (ablation)AttnFlow-iMap · MNISTbits/dim: 0.39 -> 0.50Hurt
Place attention after permutation or after coupling rather than earlier in the flow step (ablation)AttnFlow · CIFAR10bits/dimImproved

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