CATVis: Context-Aware Thought Visualization
This work addresses the problem of noisy EEG signal interpretation for brain-computer interface applications, offering incremental advancements in visual decoding.
The paper tackles the challenge of decoding visual representations from EEG signals by proposing a 5-stage framework for EEG-to-image generation, resulting in improvements such as a 13.43% increase in Classification Accuracy and a 36.61% reduction in Fréchet Inception Distance compared to state-of-the-art methods.
EEG-based brain-computer interfaces (BCIs) have shown promise in various applications, such as motor imagery and cognitive state monitoring. However, decoding visual representations from EEG signals remains a significant challenge due to their complex and noisy nature. We thus propose a novel 5-stage framework for decoding visual representations from EEG signals: (1) an EEG encoder for concept classification, (2) cross-modal alignment of EEG and text embeddings in CLIP feature space, (3) caption refinement via re-ranking, (4) weighted interpolation of concept and caption embeddings for richer semantics, and (5) image generation using a pre-trained Stable Diffusion model. We enable context-aware EEG-to-image generation through cross-modal alignment and re-ranking. Experimental results demonstrate that our method generates high-quality images aligned with visual stimuli, outperforming SOTA approaches by 13.43% in Classification Accuracy, 15.21% in Generation Accuracy and reducing Fréchet Inception Distance by 36.61%, indicating superior semantic alignment and image quality.