Research map / Label-efficient and robust learning / Recognition and long-tail
A Conflict-aware Evidential Framework for Reliable Sleep Stage Classification
Yunzhi Tian, Dekui Wang, Qirong Bu, Wei Zhou, Xingxing Hao, Jun Feng
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 conflict-aware aggregation (CMAM) instead of average fusion (ablation) | ConfSleepNet · MASS-SS3 | accuracy: 87.4 -> 88.9 | Improved |
| add CMAM instead of average fusion | ConfSleepNet · SleepEDF-20 | accuracy: 86.3 -> 87.2 | Improved |
| add CMAM instead of average fusion | ConfSleepNet · SleepEDF-78 | accuracy: 84.2 -> 85.3 | Improved |
| add CMAM instead of average fusion | ConfSleepNet · SHHS | accuracy: 87.4 -> 88.2 | Improved |
| use CMAM instead of prior fusion method (ablation) | ConfSleepNet · MASS-SS3 | accuracy: 88.4 -> 88.9 | Improved |
| add evidence mapping layer with hybrid coarse/fine categories (ablation) | ConfSleepNet · MASS-SS3 | accuracy: 88.0 -> 88.9 | Improved |
| add evidence mapping layer with hybrid categories (ablation) | ConfSleepNet · MASS-SS3 | macro-F1: 83.2 -> 84.2 | Improved |
| use learnable mapping instead of uniform mapping (ablation) | ConfSleepNet · MASS-SS3 | accuracy: 88.9 -> 88.7 | No clear effect |
| use data-driven mapping instead of uniform mapping (ablation) | ConfSleepNet · MASS-SS3 | accuracy: 88.9 -> 89.1 | No clear effect |
| use CMAM versus TMCEK uncertainty-aware baseline | ConfSleepNet · four sleep datasets | accuracy: 2.2%-4.9% accuracy gains | Improved |
| use CMAM versus best prior fusion on multi-view benchmarks | CMAM · Scene15 | accuracy: 72.60 -> 73.01 | Improved |
| use CMAM versus CCML on HandWritten | CMAM · HW | accuracy: 98.75 -> 98.45 | Hurt |
Closest papers by meaning
- Trusted Multi-View Classification with Expert Knowledge Constraints (ICML 2025 · similarity 0.85)
- Robust Sleep Staging over Incomplete Multimodal Physiological Signals via Contrastive Imagination (NeurIPS 2024 · similarity 0.85)
- Generalizable Sleep Staging via Multi-Level Domain Alignment (AAAI 2024 · similarity 0.84)
- SleepFM: Multi-modal Representation Learning for Sleep Across Brain Activity, ECG and Respiratory Signals (ICML 2024 · similarity 0.84)
- Navigating Conflicting Views: Harnessing Trust for Learning (ICML 2025 · similarity 0.83)
- Reliable Conflictive Multi-View Learning (AAAI 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.
