Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning
CSLP-AE: A Contrastive Split-Latent Permutation Autoencoder Framework for Zero-Shot Electroencephalography Signal Conversion
Anders Vestergaard Nørskov, Alexander Neergaard Zahid, Morten Mørup
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 latent permutation loss to autoencoder (AE -> SLP-AE) (ablation) | AE · ERP Core | subject accuracy: 60.68 -> 74.63 | Improved |
| add latent permutation loss to autoencoder (AE -> SLP-AE) (ablation) | AE · ERP Core | task accuracy: 31.43 -> 47.00 | Improved |
| add latent permutation loss to C-AE (C-AE -> CSLP-AE) (ablation) | C-AE · ERP Core | subject accuracy: 79.42 -> 80.32 | Improved |
| add latent permutation loss to C-AE (C-AE -> CSLP-AE) (ablation) | C-AE · ERP Core | ERP conversion MSE (D.s., S.t.): 11.33 -> 5.80 | Improved |
| add latent permutation loss to C-AE (C-AE -> CSLP-AE) (ablation) | C-AE · ERP Core | ERP conversion MSE (S.s., D.t.): 10.64 -> 6.65 | Improved |
| add contrastive loss to SLP-AE (SLP-AE -> CSLP-AE) (ablation) | SLP-AE · ERP Core | subject accuracy: 74.63 -> 80.32 | Improved |
| add contrastive loss to SLP-AE (SLP-AE -> CSLP-AE) (ablation) | SLP-AE · ERP Core | task-on-subject accuracy (disentanglement): 47.23 -> 45.41 | Mixed |
| add latent permutation to CSLP-AE objective on conversion with different subject and task (ablation) | C-AE · ERP Core | ERP conversion MSE (D.s., D.t.): 20.28 -> 20.06 | No clear effect |
| add contrastive loss to standard AE (AE -> C-AE) (ablation) | AE · ERP Core | task-on-subject accuracy: 31.62 -> 37.34 | Improved |
| add contrastive loss to standard AE (AE -> C-AE) (ablation) | AE · ERP Core | ERP conversion MSE (D.s., S.t.): 11.20 -> 11.33 | No clear effect |
| replace latent permutation with quadruplet permutation loss (SQP-AE vs SLP-AE) (ablation) | SLP-AE · ERP Core, 1s epoch | ERP conversion MSE (D.s., D.t.): 19.92 -> 6.49 | Improved |
| quadruplet permutation loss instead of latent permutation (CSQP-AE vs CSLP-AE) (ablation) | CSLP-AE · ERP Core | subject accuracy: 80.32 -> 73.04 | Hurt |
Closest papers by meaning
- MindAlign: Bridging EEG, Vision, and Language for Zero-Shot Visual Decoding (NeurIPS 2026 · similarity 0.88)
- EEGPT: Pretrained Transformer for Universal and Reliable Representation of EEG Signals (NeurIPS 2024 · similarity 0.86)
- CSBrain: A Cross-scale Spatiotemporal Brain Foundation Model for EEG Decoding (NeurIPS 2025 · similarity 0.86)
- CBraMod: A Criss-Cross Brain Foundation Model for EEG Decoding (ICLR 2025 · similarity 0.86)
- DMMR: Cross-Subject Domain Generalization for EEG-Based Emotion Recognition via Denoising Mixed Mutual Reconstruction (AAAI 2024 · similarity 0.86)
- Pre-Training Graph Contrastive Masked Autoencoders are Strong Distillers for EEG (ICML 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.
