AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

S2GAN: Share Aging Factors Across Ages and Share Aging Trends Among Individuals

Zhenliang He, Meina Kan, Shiguang Shan, Xilin Chen

ICCV 2019 · Label-efficient and robust learning › Recognition and long-tail · approach: Fair and quality-aware face recognition · 52 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
S2GAN vs IPCGAN on aging accuracy, group 51+S2GAN · MORPHaging accuracy: 56.4% -> 89.3%Improved
S2GAN vs IPCGAN on aging accuracy, group 41-50S2GAN · CACDaging accuracy: 75.6% -> 95.2%Improved
S2GAN vs IPCGAN on average face verificationS2GAN · MORPHface verification rate: 98.95% -> 99.69%Improved
S2GAN vs IPCGAN on average face verificationS2GAN · CACDface verification rate: 91.40% -> 98.91%Improved
S2GAN vs IPCGAN on hardest verification pairS2GAN · MORPHface verification rate: 86.80% -> 96.08%Improved
S2GAN vs IPCGAN on FIDS2GAN · MORPHFID: 10.4 -> 9.3Improved
S2GAN vs IPCGAN on FIDS2GAN · CACDFID: 9.1 -> 8.4Improved
S2GAN vs IPCGAN in user studyS2GAN · MORPHproportion chosen best: 22% -> 77%Improved
S2GAN vs IPCGAN in user studyS2GAN · CACDproportion chosen best: 33% -> 66%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