Human-Aligned Image Models Improve Visual Decoding from the Brain

TL;DR

This paper demonstrates that using human-aligned image encoders significantly enhances the accuracy of decoding visual images from brain activity, advancing brain-computer interface capabilities.

Contribution

Introducing human-aligned image encoders for brain-to-image decoding, leading to improved accuracy over existing methods across various datasets and modalities.

Findings

Up to 21% improvement in image retrieval accuracy.

Consistent performance gains across multiple EEG architectures and brain imaging modalities.

Effective across diverse participants and alignment methods.

Abstract

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