Research map / Label-efficient and robust learning / Domain adaptation and generalization
SPD domain-specific batch normalization to crack interpretable unsupervised domain adaptation in EEG
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 |
|---|---|---|---|
| replace SPDBN with proposed SPDMBN (adaptive momentum) (ablation) | TSMNet with DSBN · mental imagery inter-session (138 subjects) | delta balanced accuracy: -1.6 (SPDBN vs SPDMBN) | Helped |
| add domain-specific batch normalization (ablation) | TSMNet on SPD manifold · mental imagery inter-session | delta balanced accuracy: -3.9 without DSBN | Helped |
| add domain-specific batch normalization (ablation) | Euclidean network (no SPD) · mental imagery inter-session | delta balanced accuracy: -6.9 -> -4.5 | Helped |
| use SPD manifold representation instead of Euclidean variance pooling with log activations (ablation) | TSMNet · mental imagery inter-session | delta balanced accuracy: -4.5 with DSBN, -3 w/o DSBN when omitted | Helped |
| use SPD manifold (ablation) | TSMNet · mental imagery inter-session | fit time: 6.6 -> 16.9 s | Hurt |
| TSMNet vs domain-specific reference and UDA baselines | BNCI2015001 inter-subject · BNCI2015001 inter-subject | balanced accuracy: 70.3 -> 77.0 vs URPA+MDM | Helped |
| TSMNet vs FBCSP+DSS+LDA on BNCI2014001 inter-session | TSMNet · BNCI2014001 inter-session | balanced accuracy: 71.3 -> 69.0 | No clear effect |
Closest papers by meaning
- SPDIM: Source-Free Unsupervised Conditional and Label Shift Adaptation in EEG (ICLR 2025 · similarity 0.92)
- Geodesic Optimization for Predictive Shift Adaptation on EEG data (NeurIPS 2024 · similarity 0.89)
- LAtte: Hyperbolic Lorentz Attention for Joint-Subject EEG Classification (NeurIPS 2026 · similarity 0.86)
- THD-BAR: Topology Hierarchical Derived Brain Autoregressive Modeling for EEG Generic Representations (NeurIPS 2025 · similarity 0.85)
- NeurIPT: Foundation Model for Neural Interfaces (NeurIPS 2025 · similarity 0.85)
- CSBrain: A Cross-scale Spatiotemporal Brain Foundation Model for EEG Decoding (NeurIPS 2025 · 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.