AI Paper Atlas

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

Sliced Iterative Normalizing Flows

Biwei Dai, Uros Seljak

ICML 2021 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Expressive invertible architectures · 9 citations (OpenAlex)

Read the paper

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
Use SIG instead of SWF for image generationIterative image generators · MNISTFID: 225.1 -> 4.5Improved
Use SIG instead of SWF for image generationIterative image generators · Fashion-MNISTFID: 207.6 -> 13.7Improved
Use SIG instead of the best listed GAN baselineImage generators · CIFAR-10FID: 55.2 -> 66.5Hurt
Use SIG instead of the best listed GAN baselineImage generators · CelebAFID: 30.0 -> 37.3Hurt
Use SIG rather than GIS for Fashion-MNIST-trained OoD detectionSINF · MNIST OoDAUROC: 0.824 -> 0.980Improved
Use SIG rather than GIS for Fashion-MNIST-trained OoD detectionSINF · OMNIGLOT OoDAUROC: 0.891 -> 0.993Improved
Apply SIG post-processing to pretrained generator samplesSWF on Fashion-MNIST · Fashion-MNISTFID: 207.6 -> 23.9Improved
Apply SIG post-processing to pretrained generator samplesFlow-GAN (ADV) on Fashion-MNIST · Fashion-MNISTFID: 216.9 -> 21.2Improved
Apply SIG post-processing to pretrained generator samplesMAF on Fashion-MNIST · Fashion-MNISTFID: 81.2 -> 16.6Improved
Choose optimized max K-SWD axes instead of random axes (ablation)SIG · MNISTmarginal transformations to converge: two orders of magnitude fewer marginal transformationsImproved
Use optimized axes rather than random axes (ablation)SIG · MNIST samplessample qualityImproved
Add hierarchical patch-based modeling after whole-image modeling (ablation)SIG · MNIST samplessample qualityImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 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