AI Paper Atlas

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

Cooperative Training of Descriptor and Generator Networks

Jianwen Xie, Yang Lu, Ruiqi Gao, Song Chun Zhu, Ying Nian Wu

TPAMI 2018 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Score-based generative modeling analysis · 114 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
train descriptor and generator cooperatively instead of generator alone (Algorithm G) (ablation)CoopNets · ImageNet-1k scene categories (n=1100)Inception score: 2.61 -> 3.79Improved
train cooperatively instead of descriptor alone (persistent CD) (ablation)CoopNets · ImageNet-1k scene categories (n=1100)Inception score: 1.51 -> 3.79Improved
CoopNets instead of DCGAN with few training imagesCoopNets · ImageNet-1k scene categories (n=50)Inception score: 2.26 -> 2.66Improved
use descriptor with Langevin revision instead of generator output (ablation)CoopNets · LSUN bedroomsFID: 64.30 -> 35.42Improved
use descriptor with Langevin revision instead of generator output (ablation)CoopNets · CelebAFID: 16.98 -> 16.65Improved
use descriptor with Langevin revision instead of generator output (ablation)CoopNets · Cifar-10FID: 35.25 -> 33.61Improved
CoopNets generator instead of DCGANCoopNets · CelebAFID: 21.40 -> 16.98Improved
CoopNets generator instead of GANCoopNets · MNIST (Parzen window)log-likelihood: 225 -> 226Improved
CoopNets instead of DCGAN for inpaintingCoopNets · CelebA pattern completion (M30 mask)recovery error: 0.211 -> 0.115Improved
CoopNets instead of MRF-l1 inpainting at large maskCoopNets · CelebA pattern completion (M50 mask)recovery error: 0.178 -> 0.136Improved
CoopNets versus DCGAN in human rankingCoopNets · LSUN bedroomsaverage human ranking: 1.913 -> 1.700Improved

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