EEG-Deformer: A Dense Convolutional Transformer for Brain-computer Interfaces

TL;DR

EEG-Deformer introduces a novel CNN-Transformer architecture with hierarchical and dense modules to better capture temporal dynamics in EEG signals, improving brain-computer interface decoding accuracy across multiple cognitive tasks.

Contribution

The paper proposes EEG-Deformer, a new CNN-Transformer model with hierarchical and dense modules, enhancing temporal pattern learning in EEG-based BCIs.

Findings

Outperforms or matches state-of-the-art methods across three cognitive tasks.

Learns neurophysiologically meaningful brain regions.

Demonstrates strong generalizability and decoding accuracy.

Abstract

Effectively learning the temporal dynamics in electroencephalogram (EEG) signals is challenging yet essential for decoding brain activities using brain-computer interfaces (BCIs). Although Transformers are popular for their long-term sequential learning ability in the BCI field, most methods combining Transformers with convolutional neural networks (CNNs) fail to capture the coarse-to-fine temporal dynamics of EEG signals. To overcome this limitation, we introduce EEG-Deformer, which incorporates two main novel components into a CNN-Transformer: (1) a Hierarchical Coarse-to-Fine Transformer (HCT) block that integrates a Fine-grained Temporal Learning (FTL) branch into Transformers, effectively discerning coarse-to-fine temporal patterns; and (2) a Dense Information Purification (DIP) module, which utilizes multi-level, purified temporal information to enhance decoding accuracy. Comprehensive experiments on three representative cognitive tasks-cognitive attention, driving fatigue, and mental workload detection-consistently confirm the generalizability of our proposed EEG-Deformer, demonstrating that it either outperforms or performs comparably to existing state-of-the-art methods. Visualization results show that EEG-Deformer learns from neurophysiologically meaningful brain regions for the corresponding cognitive tasks. The source code can be found at https://github.com/yi-ding-cs/EEG-Deformer.