CSSSTN: A Class-sensitive Subject-to-subject Semantic Style Transfer Network for EEG Classification in RSVP Tasks

TL;DR

This paper introduces CSSSTN, a novel EEG classification network that improves cross-subject transfer learning by class-sensitive style transfer, significantly enhancing BCI performance for users with limited calibration data.

Contribution

CSSSTN is the first to incorporate class-sensitive style transfer for EEG BCI, effectively reducing calibration time and improving accuracy for BCI-illiterate users.

Findings

Outperforms state-of-the-art methods with 6.4% accuracy gain on Tsinghua dataset.

Achieves 3.5% accuracy improvement on HDU dataset.

Reduces calibration effort with minimal target data.

Abstract

The Rapid Serial Visual Presentation (RSVP) paradigm represents a promising application of electroencephalography (EEG) in Brain-Computer Interface (BCI) systems. However, cross-subject variability remains a critical challenge, particularly for BCI-illiterate users who struggle to effectively interact with these systems. To address this issue, we propose the Class-Sensitive Subject-to-Subject Semantic Style Transfer Network (CSSSTN), which incorporates a class-sensitive approach to align feature distributions between golden subjects (BCI experts) and target (BCI-illiterate) users on a class-by-class basis. Building on the SSSTN framework, CSSSTN incorporates three key components: (1) subject-specific classifier training, (2) a unique style loss to transfer class-discriminative features while preserving semantic information through a modified content loss, and (3) an ensemble approach to integrate predictions from both source and target domains. We evaluated CSSSTN using both a publicly available dataset and a self-collected dataset. Experimental results demonstrate that CSSSTN outperforms state-of-the-art methods, achieving mean balanced accuracy improvements of 6.4\% on the Tsinghua dataset and 3.5\% on the HDU dataset, with notable benefits for BCI-illiterate users. Ablation studies confirm the effectiveness of each component, particularly the class-sensitive transfer and the use of lower-layer features, which enhance transfer performance and mitigate negative transfer. Additionally, CSSSTN achieves competitive results with minimal target data, reducing calibration time and effort. These findings highlight the practical potential of CSSSTN for real-world BCI applications, offering a robust and scalable solution to improve the performance of BCI-illiterate users while minimizing reliance on extensive training data. Our code is available at https://github.com/ziyuey/CSSSTN.