Research map / Label-efficient and robust learning / Recognition and long-tail
Ordinal Regression With Multiple Output CNN 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 ordinal regression with CNN instead of metric regression with CNN | CNN age estimation · MORPH II | MAE: 3.42 -> 3.27 | Helped |
| Use ordinal regression with CNN instead of metric regression with CNN | CNN age estimation · AFAD | MAE: 3.51 -> 3.34 | Helped |
| Use data-specific task-importance weights instead of uniform task weights (ablation) | OR-CNN · MORPH II | MAE: 3.30 -> 3.27 | Helped |
| Use data-specific task-importance weights instead of uniform task weights (ablation) | OR-CNN · AFAD | MAE: 3.41 -> 3.34 | Helped |
| Use color images instead of grayscale images (ablation) | OR-CNN · MORPH II | MAE: 3.42 -> 3.27 | Helped |
| Use color images instead of grayscale images (ablation) | OR-CNN · AFAD | MAE: 3.44 -> 3.34 | Helped |
| Use end-to-end CNN ordinal regression instead of BIF features with OHRank | Age estimation · MORPH II | MAE: 3.82 -> 3.27 | Helped |
| Use end-to-end CNN ordinal regression instead of BIF features with OHRank | Age estimation · AFAD | MAE: 3.84 -> 3.34 | Helped |
Closest papers by meaning
- Using Ranking-CNN for Age Estimation (CVPR 2017 · similarity 0.91)
- Deep Regression Forests for Age Estimation (CVPR 2018 · similarity 0.89)
- Age Progression and Regression with Spatial Attention Modules (AAAI 2020 · similarity 0.86)
- Latent Factor Guided Convolutional Neural Networks for Age-Invariant Face Recognition (CVPR 2016 · similarity 0.86)
- Mean-Variance Loss for Deep Age Estimation From a Face (CVPR 2018 · similarity 0.86)
- 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)
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.