S-JEPA: towards seamless cross-dataset transfer through dynamic spatial attention
This is an incremental study addressing cross-dataset transfer for EEG signal processing in brain-computer interfaces.
The paper tackled the challenge of cross-dataset transfer in EEG signal processing by introducing Signal-JEPA with a novel spatial block masking strategy, achieving preliminary results that highlight the importance of spatial filtering and the influence of pre-training example length on downstream classification across three BCI paradigms.
Motivated by the challenge of seamless cross-dataset transfer in EEG signal processing, this article presents an exploratory study on the use of Joint Embedding Predictive Architectures (JEPAs). In recent years, self-supervised learning has emerged as a promising approach for transfer learning in various domains. However, its application to EEG signals remains largely unexplored. In this article, we introduce Signal-JEPA for representing EEG recordings which includes a novel domain-specific spatial block masking strategy and three novel architectures for downstream classification. The study is conducted on a 54 subjects dataset and the downstream performance of the models is evaluated on three different BCI paradigms: motor imagery, ERP and SSVEP. Our study provides preliminary evidence for the potential of JEPAs in EEG signal encoding. Notably, our results highlight the importance of spatial filtering for accurate downstream classification and reveal an influence of the length of the pre-training examples but not of the mask size on the downstream performance.