AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Universal EEG Epilepsy Detection via Evidential Multi-View De-Biasing

Ziqi Wen, Cai Xu, Wanqing Zhao, Jie Zhao, Wei Zhao

AAAI 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Uncertainty-aware multi-view learning · 0 citations (OpenAlex)

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 changedWhereMeasuredEffect
add the bias-elimination loss LH to the fusion-only multi-view model (ablation)BF-EML · CHB-MIT Universal-Newaccuracy: 83.76 -> 94.13Improved
add the inter-view shift calibration loss LM (ablation)BF-EML · CHB-MIT Universal-Newaccuracy: 94.13 -> 97.65Improved
add the bias-elimination loss LH to the fusion-only multi-view model (ablation)BF-EML · CHB-MIT Universal-Oldaccuracy: 91.14 -> 96.58Improved
add the inter-view shift calibration loss LM (ablation)BF-EML · CHB-MIT Universal-Oldaccuracy: 96.58 -> 99.02Improved
add the bias-elimination loss LH to the fusion-only multi-view model (ablation)BF-EML · CHB-MIT Singleaccuracy: 97.39 -> 99.06Improved
add the inter-view shift calibration loss LM (ablation)BF-EML · CHB-MIT Singleaccuracy: 99.06 -> 99.73Improved
use multi-view fusion LF instead of single-view LH only (ablation)BF-EML · CHB-MIT Singleaccuracy: Single: 91.06 vs 97.39; Universal-New: 89.08 vs 83.76Mixed
add more training patients incrementally (10% of 400 each round)BF-EML · Clinical datasetaccuracyImproved
compare against domain-adaptation JPDDA in unseen-patient settingBF-EML · CHB-MIT Universal-Newaccuracy: 93.79 -> 97.65Improved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy