MindShot: A Few-Shot Brain Decoding Framework via Transferring Cross-Subject Prior and Distilling Frequency Domain Knowledge

TL;DR

MindShot is a novel few-shot brain decoding framework that leverages cross-subject prior transfer and frequency domain knowledge distillation to reconstruct visual stimuli from fMRI signals with high accuracy and minimal data.

Contribution

It introduces a two-stage framework combining multi-subject pretraining and Fourier-based knowledge distillation, enabling effective decoding with limited data and addressing individual differences.

Findings

Achieves high semantic fidelity in visual reconstruction.

Reduces scanning time by up to 99%.

Surpasses existing methods in accuracy with minimal data.

Abstract

Aiming to reconstruct visual stimuli from brain signals, brain decoding has recently made significant progress using functional magnetic resonance imaging (fMRI). However, it still has challenging issues such as substantial individual differences and high data collection costs. To simplify these problems, most methods adopt the per-subject-per-model paradigm, but this greatly limits their applications. In this paper, we design a few-shot brain decoding setting specifically for potential clinical scenarios and propose a novel two-stage decoding framework named MindShot, comprising a Multi-Subject Pretraining (MSP) stage and Fourier-based cross-subject Knowledge Distillation (FKD) stage. Firstly, a MSP framework based on multi-modal contrastive learning is constructed to mine the cross-subject prior. Secondly, the FKD is presented to decrease inter-individual differences while improving the decoding adaptability to new individuals. Our approach achieves high semantic fidelity in visual reconstruction on the largest dataset and has the potential to reduce scanning time by up to 99%. Remarkably, MindShot achieves a CLIP accuracy of 83.6% using only 1.8% of the fMRI-image pairs, surpassing the 77.4% accuracy of the method trained on the entire NSD dataset. This makes it feasible to train large-scale brain decoding frameworks that require less data, facilitating practical applications. The code is available at https://github.com/JSinBUPT/MindShot.