An Evoked Potential-Guided Deep Learning Brain Representation For Visual Classification

TL;DR

This paper introduces a deep learning framework guided by EEG-recorded visual evoked potentials for classifying visual objects, demonstrating improved accuracy over existing methods and highlighting the potential of brain signals in visual recognition tasks.

Contribution

The study presents a novel ERP-guided LSTM framework that effectively decodes brain activity for visual classification, outperforming traditional approaches.

Findings

Achieved 66.81% accuracy for 6-category classification

Achieved 27.08% accuracy for 72-exemplar classification

Outperformed existing frameworks by 12.62% to 53.99% in accuracy

Abstract

The new perspective in visual classification aims to decode the feature representation of visual objects from human brain activities. Recording electroencephalogram (EEG) from the brain cortex has been seen as a prevalent approach to understand the cognition process of an image classification task. In this study, we proposed a deep learning framework guided by the visual evoked potentials, called the Event-Related Potential (ERP)-Long short-term memory (LSTM) framework, extracted by EEG signals for visual classification. In specific, we first extracted the ERP sequences from multiple EEG channels to response image stimuli-related information. Then, we trained an LSTM network to learn the feature representation space of visual objects for classification. In the experiment, 10 subjects were recorded by over 50,000 EEG trials from an image dataset with 6 categories, including a total of 72 exemplars. Our results showed that our proposed ERP-LSTM framework could achieve classification accuracies of cross-subject of 66.81% and 27.08% for categories (6 classes) and exemplars (72 classes), respectively. Our results outperformed that of using the existing visual classification frameworks, by improving classification accuracies in the range of 12.62% - 53.99%. Our findings suggested that decoding visual evoked potentials from EEG signals is an effective strategy to learn discriminative brain representations for visual classification.