DARE-EEG is a self-supervised EEG foundation model that enforces mask-invariance via contrastive mask alignment and momentum anchor alignment, plus conv-linear-probing for heterogeneous setups, achieving SOTA accuracy and cross-dataset portability.
Self-Supervised Electroencephalogram Representation Learning for Automatic Sleep Staging: Model Development and Evaluation Study
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Sleep-only contrastive pretraining improves results on non-sleep EEG and ECG tasks relative to training from scratch and matches or exceeds some specialized models.
citing papers explorer
-
DARE-EEG: A Foundation Model for Mining Dual-Aligned Representation of EEG
DARE-EEG is a self-supervised EEG foundation model that enforces mask-invariance via contrastive mask alignment and momentum anchor alignment, plus conv-linear-probing for heterogeneous setups, achieving SOTA accuracy and cross-dataset portability.
-
Pretraining on Sleep Data Improves non-Sleep Biosignal Tasks
Sleep-only contrastive pretraining improves results on non-sleep EEG and ECG tasks relative to training from scratch and matches or exceeds some specialized models.