Research map / Label-efficient and robust learning / Recognition and long-tail
Fairness-Aware Multi-view Evidential Learning with Adaptive Prior
Haishun Chen, Cai Xu, Jinlong Yu, Yilin Zhang, Ziyu Guan, Wei Zhao, Fangyuan Zhao, Xin Yang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 adaptive prior (ablation) | multi-view evidential baseline · Caltech-101 | ACC (%): 73.8 -> 79.1 | Improved |
| add fairness constraint to adaptive prior (ablation) | FAML w/o consistency · Caltech-101 | ACC (%): 79.1 -> 84.3 | Improved |
| add consistency regularization to adaptive prior (ablation) | FAML w/o fairness · Caltech-101 | ACC (%): 79.1 -> 80.0 | Improved |
| add consistency regularization to prior + fairness (ablation) | FAML · Caltech-101 | ACC (%): 84.3 -> 87.1 | Improved |
| add fairness constraint to prior + consistency (ablation) | FAML · Caltech-101 | ACC (%): 80.0 -> 87.1 | Improved |
| FAML vs best baseline ETMC | FAML · Handwritten | ACC (%): 90.2 -> 94.2 | Improved |
| FAML vs best baseline ETMC | FAML · Scene15 | ACC (%): 50.2 -> 57.2 | Improved |
| FAML vs best baseline R-EDL | FAML · YaleB | ACC (%): 85.4 -> 88.3 | Improved |
| FAML vs TLC on calibration | FAML · YaleB | ECE (%): 29.9 -> 10.9 | Improved |
| FAML vs ECML on Head accuracy | FAML · Handwritten | ACC Head (%): 99.8 -> 98.3 | Hurt |
Closest papers by meaning
- Enhancing Multi-View Classification Reliability with Adaptive Rejection (AAAI 2025 · similarity 0.88)
- Reliable Conflictive Multi-View Learning (AAAI 2024 · similarity 0.88)
- Navigating Conflicting Views: Harnessing Trust for Learning (ICML 2025 · similarity 0.87)
- Deep Fuzzy Multi-view Learning for Reliable Classification (ICML 2025 · similarity 0.86)
- Enhancing Testing-Time Robustness for Trusted Multi-View Classification in the Wild (CVPR 2025 · similarity 0.85)
- The Evidence Contraction Issue in Deep Evidential Regression: Discussion and Solution (AAAI 2024 · similarity 0.85)
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.
