Inter-subject Contrastive Learning for Subject Adaptive EEG-based Visual Recognition

This paper tackles the problem of subject adaptive EEG-based visual recognition. Its goal is to accurately predict the categories of visual stimuli based on EEG signals with only a handful of samples for the target subject during training. The key challenge is how to appropriately transfer the knowledge obtained from abundant data of source subjects to the subject of interest. To this end, we introduce a novel method that allows for learning subject-independent representation by increasing the similarity of features sharing the same class but coming from different subjects. With the dedicated sampling principle, our model effectively captures the common knowledge shared across different subjects, thereby achieving promising performance for the target subject even under harsh problem settings with limited data. Specifically, on the EEG-ImageNet40 benchmark, our model records the top-1 / top-3 test accuracy of 72.6% / 91.6% when using only five EEG samples per class for the target subject. Our code is available at https://github.com/DeepBCI/Deep-BCI.

I. Introduction

Reading the human mind is one of the most attracting problems for brain-computer interface (BCI) research. Over the past decades, researchers have actively been studying how to decode the human mind from brain signals to facilitate communication or restore past memories [1]–[5]. For example, BCI systems are developed to help people with disabilities to communicate with others by recognizing what they are thinking [6]. In addition, researchers have paid much attention to interpreting visual information in the human mind and identifying the visual stimulus that a human has experienced from brain signals [7]. Recent studies have shown promising performance in recognizing the category of visual stimulus based on the brain signals [8], [9].