Research map / Architectures and efficiency / CNN design
Deep Regression Forests for Age Estimation
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 |
|---|---|---|---|
| Use DRFs instead of ARN | Age estimation · MORPH Setting I | MAE: 3.00 -> 2.91 | Helped |
| Use DRFs instead of dLDLF | Age estimation · MORPH Setting II | MAE: 2.24 -> 2.17 | Helped |
| Use DRFs instead of CPLF | Age estimation · MORPH Setting III | MAE: 3.63 -> 2.98 | Helped |
| Use DRFs instead of CAM | Age estimation · FG-NET leave-one-out | MAE: 4.12 -> 3.85 | Helped |
| Use DRFs instead of DEX | Age estimation · CACD train split | MAE: 4.785 -> 4.637 | Helped |
| Use DRFs instead of DEX | Age estimation · CACD validation split | MAE: 6.521 -> 5.768 | Helped |
| Increase the number of trees (ablation) | DRFs · MORPH Setting I | MAE | Helped |
| Increase tree depth (ablation) | DRFs · MORPH Setting I | MAE | Mixed |
Closest papers by meaning
- Ordinal Regression With Multiple Output CNN for Age Estimation (CVPR 2016 · similarity 0.89)
- Latent Factor Guided Convolutional Neural Networks for Age-Invariant Face Recognition (CVPR 2016 · similarity 0.88)
- Longitudinal Face Modeling via Temporal Deep Restricted Boltzmann Machines (CVPR 2016 · similarity 0.88)
- Deep Cost-Sensitive and Order-Preserving Feature Learning for Cross-Population Age Estimation (CVPR 2018 · similarity 0.88)
- 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 0.86)
- From Cradle to Cane: A Two-Pass Framework for High-Fidelity Lifespan Face Aging (NeurIPS 2025 · 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.