Research map / Label-efficient and robust learning / Recognition and long-tail
PML: Progressive Margin Loss for Long-Tailed Age Classification
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 progressive margin loss instead of the compared method | Facial age classification · Morph II Setting II | MAE: 2.37 -> 2.31 | Helped |
| Use progressive margin loss instead of the compared method | Facial age classification · FG-NET LOPO | MAE: 2.32 -> 2.16 | Helped |
| Use progressive margin loss instead of the compared method | Facial age classification · ChaLearn LAP 2015, without external pretraining | MAE: 3.052 -> 3.455 | Hurt |
| Pretrain PML on IMDB-WIKI | PML · ChaLearn LAP 2015 | MAE: 3.455 -> 2.915 | Helped |
| Increase training data through successive curricula | PML · Morph II | MAE: 3.751 -> 2.828 -> 2.503 -> 2.314 | Helped |
| Increase training data through successive curricula | PML · ChaLearn | MAE: 6.720 -> 5.306 -> 4.622 -> 3.878 | Helped |
| Add progressive margin loss in place of standard KL loss | Baseline model with the same architecture · FG-NET | Feature discriminativeness | Helped |
Closest papers by meaning
- Mean-Variance Loss for Deep Age Estimation From a Face (CVPR 2018 · similarity 0.87)
- Longitudinal Face Modeling via Temporal Deep Restricted Boltzmann Machines (CVPR 2016 · similarity 0.86)
- Unimodal-Concentrated Loss: Fully Adaptive Label Distribution Learning for Ordinal Regression (CVPR 2022 · similarity 0.85)
- Latent Factor Guided Convolutional Neural Networks for Age-Invariant Face Recognition (CVPR 2016 · 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 0.85)
- 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.