Reconstructing Perceived Images from Brain Activity by Visually-guided Cognitive Representation and Adversarial Learning

TL;DR

This paper presents a novel framework combining dual-variational autoencoders and GANs to reconstruct visual images from fMRI brain activity, effectively addressing data heterogeneity and high dimensionality issues.

Contribution

It introduces a three-stage learning approach for better decoding of brain signals into visual stimuli, outperforming existing methods.

Findings

Achieves high-quality image reconstruction from fMRI data.

Outperforms existing methods on artificial and natural images.

Demonstrates the effectiveness of the three-stage learning process.

Abstract

Reconstructing visual stimulus (image) only from human brain activity measured with functional Magnetic Resonance Imaging (fMRI) is a significant and meaningful task in Human-AI collaboration. However, the inconsistent distribution and representation between fMRI signals and visual images cause the heterogeneity gap. Moreover, the fMRI data is often extremely high-dimensional and contains a lot of visually-irrelevant information. Existing methods generally suffer from these issues so that a satisfactory reconstruction is still challenging. In this paper, we show that it is possible to overcome these challenges by learning visually-guided cognitive latent representations from the fMRI signals, and inversely decoding them to the image stimuli. The resulting framework is called Dual-Variational Autoencoder/ Generative Adversarial Network (D-VAE/GAN), which combines the advantages of adversarial representation learning with knowledge distillation. In addition, we introduce a novel three-stage learning approach which enables the (cognitive) encoder to gradually distill useful knowledge from the paired (visual) encoder during the learning process. Extensive experimental results on both artificial and natural images have demonstrated that our method could achieve surprisingly good results and outperform all other alternatives.