Research map / Image generation / GANs
Learning Continuous Face Age Progression: A Pyramid of GANs
Hongyu Yang, Di Huang, Yunhong Wang, Anil K. Jain
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add pyramid-structured discriminator over one-pathway discriminator (ablation) | age progression GAN · CACD | mean absolute age error (years): 2.48 -> 0.99 | Improved |
| add pyramid-structured discriminator over one-pathway discriminator (ablation) | age progression GAN · MORPH | mean absolute age error (years): 2.67 -> 0.85 | Improved |
| add pyramid discriminator (ablation) | age progression GAN · CACD | verification confidence, aged face 3: 87.43 -> 91.22 | Improved |
| add pyramid discriminator (ablation) | age progression GAN · MORPH | verification confidence, aged face 3: 86.94 -> 88.12 | Improved |
| add pyramid discriminator (ablation) | age progression GAN · CACD | verification confidence, aged face 1: 95.51 -> 94.61 | Hurt |
| use k class-wise discriminators instead of single discriminator with k logits (ablation) | age progression GAN · qualitative faces | visual aging quality | Improved |
| add auxiliary age classifier (AC-GAN) to discriminator (ablation) | age progression GAN · qualitative faces | aging effect naturalness | No clear effect |
| independently train per age cluster models (previous work) vs joint conditional model | age progression GAN · CACD | verification rate, aged face 3 (%): 99.11% -> 99.98 | Improved |
| independently train per age cluster models (previous work) vs joint conditional model | age progression GAN · MORPH | verification rate, aged face 3 (%): 95.94% -> 99.88 | Improved |
| compare proposed method with prior work in pairwise human study | age progression GAN · 138 image pairs from published papers | preference votes (%): 71.74% vs 19.28% | Improved |
Closest papers by meaning
- Learning Face Age Progression: A Pyramid Architecture of GANs (CVPR 2018 · similarity 0.98)
- Continuous Face Aging via Self-Estimated Residual Age Embedding (CVPR 2021 · similarity 0.94)
- Face Aging With Identity-Preserved Conditional Generative Adversarial Networks (CVPR 2018 · similarity 0.92)
- Age Progression and Regression with Spatial Attention Modules (AAAI 2020 · similarity 0.92)
- Attribute-Aware Face Aging With Wavelet-Based Generative Adversarial Networks (CVPR 2019 · similarity 0.92)
- Temporal Non-Volume Preserving Approach to Facial Age-Progression and Age-Invariant Face Recognition (ICCV 2017 · similarity 0.91)
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.
