atlas

Research map / Image generation / Editing and style transfer

Face Aging With Identity-Preserved Conditional Generative Adversarial Networks

CVPR 2018 · Image generation › Editing and style transfer · approach: Identity-preserving face manipulation · 264 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
Add the age classifier module (ablation)IPCGANs · CACD user studyAge classification (%): 28.73 -> 31.37Helped
Add the identity-preserved term (ablation)IPCGANs · CACD user studyFace verification (%): 98.15 -> 99.07Helped
Use IPCGANs-generated faces for data augmentationFace VGG classifier · CACD face recognition test setFace recognition accuracy (%): 84.9% -> 84.8%No clear effect
Use CAAE-generated faces for data augmentationFace VGG classifier · CACD face recognition test setFace recognition accuracy (%): 84.9% -> 78.2%Hurt
Choose a deeper feature layer for the identity perceptual loss, from shallow layers toward deeper layers (ablation)IPCGANs · CACD face aging, input age 11-20 and target age 50+Identity preservation and aging effectMixed
Set the identity perceptual-loss feature layer to conv5 (ablation)IPCGANs · CACD face agingImage quality and identity preservationHelped

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