Human-Aligned Image Models Improve Visual Decoding from the Brain
This work addresses the challenge of brain-computer interaction and understanding human perception, but it is incremental as it modifies existing alignment approaches.
The paper tackled the problem of decoding visual images from brain activity by using human-aligned image encoders, resulting in an improvement of up to 21% in image retrieval accuracy compared to state-of-the-art methods.
Decoding visual images from brain activity has significant potential for advancing brain-computer interaction and enhancing the understanding of human perception. Recent approaches align the representation spaces of images and brain activity to enable visual decoding. In this paper, we introduce the use of human-aligned image encoders to map brain signals to images. We hypothesize that these models more effectively capture perceptual attributes associated with the rapid visual stimuli presentations commonly used in visual brain data recording experiments. Our empirical results support this hypothesis, demonstrating that this simple modification improves image retrieval accuracy by up to 21% compared to state-of-the-art methods. Comprehensive experiments confirm consistent performance improvements across diverse EEG architectures, image encoders, alignment methods, participants, and brain imaging modalities