Research map / Label-efficient and robust learning / Recognition and long-tail
Deep Cost-Sensitive and Order-Preserving Feature Learning for Cross-Population 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 DCP instead of JML | cross-population age estimation · Morph II BM→BF; BM→WF; WM→BF; WM→WF | MAE (years): 5.56 -> 3.75; 5.57 -> 3.18; 6.40 -> 3.90; 5.00 -> 3.13 | Helped |
| Use DCP instead of DJML | cross-population age estimation · Morph II and WebFace | MAE (years): 3.81 -> 3.75; 3.30 -> 3.18; 4.00 -> 3.90; 3.20 -> 3.13; 4.73 -> 4.61; 4.80 -> 4.65; 4.72 -> 4.60; 4.40 -> 4.33 | Helped |
| Add cost-sensitive weighting to the multi-task loss (ablation) | MTNet age estimation · Morph II and WebFace source-population test splits | MAE (years): 3.39 -> 3.37; 2.84 -> 2.80; 6.85 -> 6.64; 7.17 -> 6.90 | Helped |
| Use age-gap weighting in pairwise alignment (ablation) | DCP · Morph II BM→BF; BM→WF; WM→BF; WM→WF | MAE (years): 3.87 -> 3.75; 3.30 -> 3.18; 3.98 -> 3.90; 3.23 -> 3.13 | Helped |
| Use age-gap weighting in pairwise alignment (ablation) | DCP · WebFace WM→YM; WM→YF; WF→YM; WF→YF | MAE (years): 4.72 -> 4.61; 4.75 -> 4.65; 4.74 -> 4.60; 4.43 -> 4.33 | Helped |
| Reduce the target-population training set (ablation) | DCP · Morph II BM→BF | MAE (years): 3.75; 3.80; 3.90; 4.09; 4.12; 4.30; 4.40; 4.61; 4.97; 5.30 | Hurt |
Closest papers by meaning
- Look across Elapse: Disentangled Representation Learning and Photorealistic Cross-Age Face Synthesis for Age-Invariant Face Recognition (AAAI 2019 · similarity 0.89)
- Mean-Variance Loss for Deep Age Estimation From a Face (CVPR 2018 · similarity 0.88)
- Deep Regression Forests for Age Estimation (CVPR 2018 · similarity 0.88)
- From Cradle to Cane: A Two-Pass Framework for High-Fidelity Lifespan Face Aging (NeurIPS 2025 · similarity 0.87)
- Longitudinal Face Modeling via Temporal Deep Restricted Boltzmann Machines (CVPR 2016 · 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 0.87)
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.