Research map / Label-efficient and robust learning / Recognition and long-tail
Relative Uncertainty Learning for Facial Expression Recognition
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 |
|---|---|---|---|
| add relative uncertainty learning (feature mixup with add-up loss) vs SCN | ResNet-18 · RAF-DB 30% noise | accuracy (%): 77.46 -> 82.06 | Helped |
| RUL vs DUL under label noise | ResNet-18 · FER2013 30% noise | accuracy (%): 60.98 -> 64.62 | Helped |
| RUL vs DUL under label noise | ResNet-18 · AffectNet 30% noise | accuracy (%): 55.09 -> 56.65 | Helped |
| RUL vs DUL with rejection | ResNet-18 · RAF-DB 30% rejection | accuracy (%): 94.50 -> 97.35 | Helped |
| RUL vs CONF at 30% rejection | ResNet-18 · CIFAR-10 | accuracy (%): 99.56 -> 99.44 | Hurt |
| RUL vs DUL on ImageNet-100 without rejection | ResNet-18 · ImageNet-100 | accuracy (%): 76.03 -> 77.74 | Helped |
| mix features instead of mixing logits (ablation) | RUL · RAF-DB | accuracy (%): 88.36 -> 88.98 | Helped |
| mix features instead of weighting loss by uncertainty (ablation) | RUL · RAF-DB 10% rejection | accuracy (%): 89.32 -> 92.72 | Helped |
| replace DUL Gaussian variances with RUL uncertainty | DUL · RAF-DB | accuracy (%): 88.17 -> 88.75 | Helped |
Closest papers by meaning
- Navigating Label Ambiguity for Facial Expression Recognition in the Wild (AAAI 2025 · similarity 0.88)
- Data Uncertainty Learning in Face Recognition (CVPR 2020 · similarity 0.87)
- Open-Set Facial Expression Recognition (AAAI 2024 · similarity 0.86)
- Facial-R1: Aligning Reasoning and Recognition for Facial Emotion Analysis (AAAI 2026 · similarity 0.85)
- FAIR-FER: A Latent Alignment Approach for Mitigating Bias in Facial Expression Recognition (Student Abstract) (AAAI 2024 · similarity 0.85)
- Multi-Energy Guided Image Translation with Stochastic Differential Equations for Near-Infrared Facial Expression Recognition (AAAI 2024 · 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.