Research map / Image generation / GANs
Age Progression and Regression with Spatial Attention Modules
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add spatial attention modules to generators (ablation) | age progression/regression cGAN · UTKFace | age estimation error: 6.81 -> 4.77 | Helped |
| add spatial attention modules to generators (ablation) | age progression/regression cGAN · CACD | age estimation error: 1.89 -> 1.78 | Helped |
| add spatial attention modules to generators (ablation) | age progression/regression cGAN · Morph | age estimation error: 1.53 -> 1.53 | No clear effect |
| use age-ordered input pairs instead of unordered (ablation) | age progression/regression cGAN · UTKFace | age estimation error: 5.49 -> 4.77 | Helped |
| use age-ordered input pairs instead of unordered (ablation) | age progression/regression cGAN · CACD | age estimation error: 1.92 -> 1.78 | Helped |
| use attention-based generators instead of Dual cGANs (no attention) | face aging · UTKFace | verification rate (%): 92.29 -> 98.10 | Helped |
| use attention-based pair of generators instead of IPCGAN | face aging · CACD | age estimation error: 8.11 -> 1.78 | Helped |
Closest papers by meaning
- Learning Face Age Progression: A Pyramid Architecture of GANs (CVPR 2018 · similarity 0.92)
- Age Progression/Regression by Conditional Adversarial Autoencoder (CVPR 2017 · similarity 0.92)
- From Cradle to Cane: A Two-Pass Framework for High-Fidelity Lifespan Face Aging (NeurIPS 2025 · similarity 0.87)
- A Call to Reflect on Evaluation Practices for Age Estimation: Comparative Analysis of the State-of-the-Art and a Unified Benchmark (CVPR 2024 · similarity 0.85)
- Limitations of Face Image Generation (AAAI 2024 · similarity 0.84)
- Diffusion-driven GAN Inversion for Multi-Modal Face Image Generation (CVPR 2024 · similarity 0.84)
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.