AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Probabilistic Neural Programmed Networks for Scene Generation

Zhiwei Deng, Jiacheng Chen, YIFANG FU, Greg Mori

NeurIPS 2018 · Image generation › Autoregressive and latent generation · approach: Compositional scene generation · 15 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 PNP-Net instead of DC-GAN/PixelCNN/PoE-VAE baselinesPNP-Net · CLEVR-GOBJ-A detector mAP: 0.176 -> 0.737 (vs DC-GAN)Improved
use PNP-Net instead of baselinesPNP-Net · CLEVR-G zero-shotOBJ-A detector mAP: 0.332 -> 0.734 (vs DC-GAN)Improved
use PNP-Net instead of baselinesPNP-Net · ColorMNISTOBJ-A detector mAP: 0.318 -> 0.363 (vs PixelCNN)Improved
use PNP-Net instead of PixelCNN/DC-GANPNP-Net · ColorMNISTOBJ-N detector mAP: 0.990 -> 0.981 (vs DC-GAN)Hurt
use gated PoE instead of plain PoE in combine operator (ablation)PNP-Net · ColorMNISTdetector score: 2-3% boostImproved
train on up-to-4-object scenes instead of up-to-8 and test on up-to-8 (ablation)PNP-Net · CLEVR-G 128x128 up to 8 objectsOBJ-A detector mAP: 0.567 -> 0.518Hurt

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