Research map / Architectures and efficiency / CNN design
C3AE: Exploring the Limits of Compact Model for Age Estimation
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 |
|---|---|---|---|
| Use C3AE's compact standard-convolution plain model instead of MobileNet-V2 or ShuffleNet-V2 | C3AE Plain model · Morph II | MAE: 3.13 vs 3.24 | Helped |
| Add a residual module (ablation) | C3AE Plain model · Morph II | MAE: 3.13 -> 3.21 | Hurt |
| Add a residual module (ablation) | C3AE Plain model · IMDB | MAE: 6.57 -> 6.66 | Hurt |
| Add a residual module (ablation) | C3AE Plain model · WIKI | MAE: 6.44 -> 6.57 | Hurt |
| Add an SE module (ablation) | C3AE Plain model · Morph II | MAE: 3.13 -> 3.11 | Helped |
| Add an SE module (ablation) | C3AE Plain model · IMDB | MAE: 6.57 -> 6.50 | Helped |
| Add an SE module (ablation) | C3AE Plain model · WIKI | MAE: 6.44 -> 6.36 | Helped |
| Add cascade training with two-points age representation (ablation) | C3AE · Morph II | MAE | Helped |
| Add the multi-scale context module (ablation) | C3AE with cascade module · Morph II | MAE | Helped |
| Use IMDB-WIKI pretraining rather than training from scratch | C3AE Full model · Morph II | MAE: 2.78 -> 2.75 | Helped |
| Vary the cascade loss weight alpha among 5, 8, 10, 12, and 15 (ablation) | C3AE Full model · Morph II | MAE: 2.79, 2.79, 2.75, 2.79 and 2.80 | No clear effect |
Closest papers by meaning
- BridgeNet: A Continuity-Aware Probabilistic Network for Age Estimation (CVPR 2019 · similarity 0.85)
- Using Ranking-CNN for Age Estimation (CVPR 2017 · similarity 0.85)
- Deep Cost-Sensitive and Order-Preserving Feature Learning for Cross-Population Age Estimation (CVPR 2018 · similarity 0.85)
- 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 0.83)
- From Cradle to Cane: A Two-Pass Framework for High-Fidelity Lifespan Face Aging (NeurIPS 2025 · similarity 0.81)
- Few-Class Arena: A Benchmark for Efficient Selection of Vision Models and Dataset Difficulty Measurement (ICLR 2025 · similarity 0.79)
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.