atlas

Research map / Image generation / GANs

Learning Face Age Progression: A Pyramid Architecture of GANs

CVPR 2018 · Image generation › GANs · approach: GAN-based image manipulation · 201 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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 a pyramid discriminator instead of a one-pathway discriminator (ablation)Face age progression GAN · MORPH and CACDmean absolute error of estimated age across three age clusters: 2.69 and 2.52 years for one-pathway; 0.79 and 0.50 years for pyramidHelped
use a pyramid discriminator instead of a one-pathway discriminator (ablation)Face age progression GAN · MORPH and CACDverification confidence: Table 2 vs Table 3Helped
progress faces into older age clustersPyramid GAN · MORPH and CACDestimated age: MORPH: 42.84, 50.78, and 59.91; CACD: 44.29, 48.34, and 52.02Helped
preserve identity using the input-output face descriptor lossPyramid GAN · MORPH and CACDverification rate: MORPH: 100%, 98.91%, and 93.09%; CACD: 99.99%, 99.91%, and 98.28%Helped
evaluate age progression with human pairwise preferencesPyramid GAN · 138 paired images from 54 individualsshare of observer votes favoring the method: 69.78% favor the proposed method, 20.80% favor the prior work, and 9.42% indicate that they are about the sameHelped

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