EEG-ConvTransformer for single-trial EEG-based visual stimulus classification

作者：

Highlights：

• Introduces EEG-ConvTransformer to improve EEG-based visual stimulus classification

• Leverages spatial context using inter-region interactions

• Wide variant outperforms existing methods for 5 different tasks

• Analysis of inter-head diversity shows low similarity among the head representations

摘要

•Introduces EEG-ConvTransformer to improve EEG-based visual stimulus classification•Leverages spatial context using inter-region interactions•Wide variant outperforms existing methods for 5 different tasks•Analysis of inter-head diversity shows low similarity among the head representations

论文关键词：EEG,Visual stimulus classification,Deep learning,Transformer,Multi-head attention,Inter-region similarity,Temporal convolution,Inter-head diversity,Head representations

论文评审过程：Received 24 August 2021, Revised 3 April 2022, Accepted 27 April 2022, Available online 29 April 2022, Version of Record 17 May 2022.

论文官网地址：https://doi.org/10.1016/j.patcog.2022.108757