Research map / Architectures and efficiency / Attention and transformers
SEBSFormer: A Spectral-Enhanced Bi-Stream Transformer for Robust EEG Decoding
Lin Zhang, Shikui Tu, Lei Xu
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 the spectral stream (ablation) | SEBSFormer · SEED | Kappa (%): 60.11 -> 62.62 | Improved |
| add the spectral stream (ablation) | SEBSFormer · TUEV | BAcc (%): 63.88 -> 65.95 | Improved |
| add SCM (ablation) | SEBSFormer · TUEV | Kappa (%): 66.63 -> 68.71 | Improved |
| add SCM (ablation) | SEBSFormer · TUAB | BAcc (%): 81.35 -> 82.12 | Improved |
| add MS-TAM (ablation) | SEBSFormer · TUEV | Kappa (%): 68.27 -> 68.71 | Improved |
| add GDGF (ablation) | SEBSFormer · TUEV | BAcc (%): 65.87 -> 65.95 | Improved |
| add GDGF (ablation) | SEBSFormer · TUAB | BAcc (%): 82.08 -> 82.12 | No clear effect |
| retain more high-frequency components in SCM mask (L1-H5 vs L5-H1) (ablation) | SEBSFormer · TUAB | accuracy | Improved |
| balanced low/high frequency split in SCM mask (ablation) | SEBSFormer · TUAB | accuracy | Improved |
| add SCM to Transformer (ablation) | SEBSFormer · SEED | inter-layer cosine similarity | Improved |
| use SEBSFormer over LaBraM | SEBSFormer · TUAB | AUROC: 0.9022 -> 0.9048 | No clear effect |
| use SEBSFormer over LaBraM | SEBSFormer · TUEV | Kappa: 0.6637 -> 0.6871 | Improved |
Closest papers by meaning
- EEGPT: Pretrained Transformer for Universal and Reliable Representation of EEG Signals (NeurIPS 2024 · similarity 0.88)
- CSBrain: A Cross-scale Spatiotemporal Brain Foundation Model for EEG Decoding (NeurIPS 2025 · similarity 0.87)
- MindAlign: Bridging EEG, Vision, and Language for Zero-Shot Visual Decoding (NeurIPS 2026 · similarity 0.87)
- CBraMod: A Criss-Cross Brain Foundation Model for EEG Decoding (ICLR 2025 · similarity 0.87)
- Decoding Natural Images from EEG for Object Recognition (ICLR 2024 · similarity 0.87)
- Visual Decoding and Reconstruction via EEG Embeddings with Guided Diffusion (NeurIPS 2024 · similarity 0.86)
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.
