Research map / Image generation / GANs
Attribute-Aware Face Aging With Wavelet-Based Generative Adversarial Networks
Check 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 changed | Where | Measured | Effect |
|---|---|---|---|
| Add facial attribute embedding (FAE) (ablation) | Proposed face-aging GAN · MORPH | gender and race preservation rate: Gender: 95.72, 94.21, 93.60 -> 97.37, 97.21, 96.07; Race: 95.04, 93.55, 90.83 -> 95.86, 94.10, 93.22 | Helped |
| Add wavelet packet transform (WPT) (ablation) | Proposed face-aging GAN · MORPH | age deviation: 0.44, 1.72, 3.03 -> 0.68, 0.41, 2.31 (without FAE); 0.82, 0.52, 4.82 -> 0.13, 0.19, 0.68 (with FAE) | Helped |
| Add WPT without facial attribute embedding (ablation) | Proposed face-aging GAN · MORPH | gender and race preservation: Gender: 95.72, 94.21, 93.60 -> 96.15, 94.90, 93.61; Race: 95.04, 93.55, 90.83 -> 93.89, 88.63, 90.21 | No clear effect |
| Remove WPT while retaining FAE (ablation) | Proposed face-aging GAN · MORPH | verification rate: 31-40: 100.00 -> 100.00; 41-50: 100.00 -> 100.00; 51+: 98.26 -> 98.86 | Mixed |
| Add FAE and WPT (ablation) | Proposed face-aging GAN · MORPH | gender preservation rate: 95.72, 94.21, 93.60 -> 97.37, 97.21, 96.07 | Helped |
| Rely on identity consistency without attribute supervision (ablation) | Face-aging GAN · MORPH | facial attribute preservation | Hurt |
| Use attribute-conditioned face aging | Ours vs. GLCA-GAN and PAG-GAN · CACD | gender preservation rate: 87.19 vs 85.89 (GLCA-GAN), 70.05 (PAG-GAN) | Helped |
Closest papers by meaning
- Learning Face Age Progression: A Pyramid Architecture of GANs (CVPR 2018 · similarity 0.92)
- Continuous Face Aging via Self-Estimated Residual Age Embedding (CVPR 2021 · similarity 0.91)
- Face Aging With Identity-Preserved Conditional Generative Adversarial Networks (CVPR 2018 · similarity 0.91)
- Age Progression and Regression with Spatial Attention Modules (AAAI 2020 · similarity 0.90)
- Decorrelated Adversarial Learning for Age-Invariant Face Recognition (CVPR 2019 · similarity 0.87)
- From Cradle to Cane: A Two-Pass Framework for High-Fidelity Lifespan Face Aging (NeurIPS 2025 · similarity 0.85)
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.