AI Paper Atlas

Research map / Image generation / Super-resolution

Learning Implicit Generative Models by Matching Perceptual Features

Cicero Nogueira dos Santos, Youssef Mroueh, Inkit Padhi, Pierre Dognin

ICCV 2019 · Image generation › Super-resolution · approach: Perceptual and real-world SR · 25 citations (OpenAlex)

This paper tried a common change: Larger batch size

increase minibatch size from 64 to 512 with ADAM moving average · CelebA · image quality (qualitative) No clear effect

What 785 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.

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 ImageNet VGG19 classifier features instead of VGG19 encoder features (ablation)GFMN · CIFAR10Inception Score: 4.95 -> 7.88Improved
use ImageNet VGG19 classifier features instead of VGG19 encoder features (ablation)GFMN · CIFAR10FID (50K): 57.2 -> 20.8Improved
use VGG19 + Resnet18 features together instead of VGG19 alone (ablation)GFMN · CIFAR10Inception Score: 7.88 -> 8.08Improved
use VGG19 + Resnet18 features together instead of VGG19 alone (ablation)GFMN · CIFAR10FID (50K): 20.8 -> 20.9No clear effect
replace DCGAN generator with Resnet generator (ablation)GFMN VGG19+Resnet18 · CIFAR10Inception Score: 8.08 -> 8.27Improved
replace DCGAN generator with Resnet generator (ablation)GFMN VGG19+Resnet18 · CIFAR10FID (50K): 20.9 -> 13.5Improved
increase number of VGG19 layers used for matching from 1 to 16 (ablation)GFMN VGG19 · CIFAR10Inception Score: 4.68 -> 7.88Improved
increase number of VGG19 layers from 11 to 13 (ablation)GFMN VGG19 · CIFAR10Inception Score: 7.72 -> 7.49No clear effect
add covariance matching to mean matching (VGG19 features) (ablation)GFMN · CIFAR10Inception Score: 7.42 -> 7.88Improved
add covariance matching to mean matching (DCGAN encoder features) (ablation)GFMN · CIFAR10FID (50K): 92.5 -> 78.3Improved
add covariance matching to mean matching (Resnet18 features) (ablation)GFMN · CIFAR10Inception Score: 7.03 -> 7.92Improved
replace simple moving average with ADAM moving average at minibatch size 64 (ablation)GFMN · CelebAimage quality (qualitative)Improved

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