AI Paper Atlas

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

NeurIPS 2023 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Zero-shot robustness and transfer · 2 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 latent permutation loss to autoencoder (AE -> SLP-AE) (ablation)AE · ERP Coresubject accuracy: 60.68 -> 74.63Improved
add latent permutation loss to autoencoder (AE -> SLP-AE) (ablation)AE · ERP Coretask accuracy: 31.43 -> 47.00Improved
add latent permutation loss to C-AE (C-AE -> CSLP-AE) (ablation)C-AE · ERP Coresubject accuracy: 79.42 -> 80.32Improved
add latent permutation loss to C-AE (C-AE -> CSLP-AE) (ablation)C-AE · ERP CoreERP conversion MSE (D.s., S.t.): 11.33 -> 5.80Improved
add latent permutation loss to C-AE (C-AE -> CSLP-AE) (ablation)C-AE · ERP CoreERP conversion MSE (S.s., D.t.): 10.64 -> 6.65Improved
add contrastive loss to SLP-AE (SLP-AE -> CSLP-AE) (ablation)SLP-AE · ERP Coresubject accuracy: 74.63 -> 80.32Improved
add contrastive loss to SLP-AE (SLP-AE -> CSLP-AE) (ablation)SLP-AE · ERP Coretask-on-subject accuracy (disentanglement): 47.23 -> 45.41Mixed
add latent permutation to CSLP-AE objective on conversion with different subject and task (ablation)C-AE · ERP CoreERP conversion MSE (D.s., D.t.): 20.28 -> 20.06No clear effect
add contrastive loss to standard AE (AE -> C-AE) (ablation)AE · ERP Coretask-on-subject accuracy: 31.62 -> 37.34Improved
add contrastive loss to standard AE (AE -> C-AE) (ablation)AE · ERP CoreERP conversion MSE (D.s., S.t.): 11.20 -> 11.33No clear effect
replace latent permutation with quadruplet permutation loss (SQP-AE vs SLP-AE) (ablation)SLP-AE · ERP Core, 1s epochERP conversion MSE (D.s., D.t.): 19.92 -> 6.49Improved
quadruplet permutation loss instead of latent permutation (CSQP-AE vs CSLP-AE) (ablation)CSLP-AE · ERP Coresubject accuracy: 80.32 -> 73.04Hurt

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