AI Paper Atlas

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

A Forest from the Trees: Generation through Neighborhoods

Yang Li, Tianxiang Gao, Junier Oliva

AAAI 2020 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Disentangled and discrete latent models · 3 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
Use NCT instead of RealNVPRealNVP · MNISTFID: 10.4 -> 8.2Improved
Use NCL instead of RealNVPRealNVP · SVHNFID: 103.8 -> 50.0Improved
Use NCT instead of RealNVPRealNVP · CIFAR-10FID: 99.9 -> 81.1Improved
Use NCT instead of RealNVPRealNVP · CelebAFID: 39.2 -> 30.9Improved
Use NCT instead of RealNVPRealNVP · CIFAR-10PRD (F8, F1/8): (0.322, 0.631) -> (0.568, 0.691)Improved
Use NCL instead of RealNVPRealNVP · SVHNPRD (F8, F1/8): (0.740, 0.731) -> (0.808, 0.928)Improved
Use NCL instead of RealNVPRealNVP · MNISTPRD (F8, F1/8): (0.982, 0.982) -> (0.981, 0.970)Mixed
Use neighborhood-conditioned flowRealNVP · CelebAPRD (F8, F1/8): RNVP (0.675, 0.766); NCL (0.853, 0.806); NCT (0.849, 0.821)Mixed
Add contrastive training (ablation)NCL · MNIST novelty detection (mean over classes)AUC-ROC: 0.621 -> 0.801Improved
Remove contrastive training (ablation)NCL · MNIST novelty detection (mean over classes)AUC-ROC: 0.801 -> 0.621Hurt
Use NCL instead of RealNVPRealNVP · MNIST novelty detection (mean over classes)AUC-ROC: 0.641 -> 0.621Hurt
Use NCL with contrastive training instead of RealNVPRealNVP · MNIST novelty detection (mean over classes)AUC-ROC: 0.641 -> 0.801Improved

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