StableMind: Source-Free Cross-Subject fMRI Decoding with Regularized Adaptation

2026-05-04

AI Summary

This work addresses the challenges of cross-subject fMRI decoding under conditions of limited target-subject data and inaccessibility of source data, where unstable neural responses and unreliable image supervision often hinder performance. To overcome these limitations, the authors propose StableMind, a novel framework featuring three key innovations: leveraging pre-trained ridge regression as an adaptation prior to regularize the representation space, enhancing neural response stability through Fourier-domain feature augmentation, and refining brain–image alignment via a difficulty-aware image blurring mechanism. Notably, StableMind enables efficient few-shot adaptation without requiring access to source data. Evaluated on the Natural Scenes Dataset, the method achieves 84.02% image retrieval accuracy and 81.66% brain retrieval accuracy—outperforming the current state of the art by 5.71%—while employing fewer trainable parameters.

Abstract

Existing cross-subject fMRI decoding methods typically train a model on multiple scanned subjects and then adapt it to a new subject using substantial paired fMRI-image data. However, in realistic scenarios, new-subject fMRI data are often limited due to costly data acquisition, and raw data from previous subjects may be inaccessible, leading existing methods to suffer performance degradation during new-subject adaptation. In this paper, we identify that this degradation stems from two key issues: brain-side instability caused by large subject differences in fMRI responses, and image-side supervision unreliability caused by fine-grained visual details that are not reliably supported by limited fMRI signals. To address these challenges, we propose StableMind, a regularized adaptation framework designed to improve brain-side representation stability and image-side supervision reliability. (1) To stabilize brain representations, StableMind reuses ridge projections from the pretrained model as adaptation priors to constrain limited-data new-subject adaptation, and applies Fourier-based feature-level brain augmentation to improve robustness to individual variability. (2) To improve image supervision reliability, StableMind introduces difficulty-aware image blur for brain-image alignment, reducing the influence of fine-grained visual details that are weakly supported by limited fMRI signals while preserving stable visual structure. Experiments on the Natural Scenes Dataset under a unified 1-hour adaptation protocol demonstrate that StableMind achieves 84.02% image retrieval accuracy and 81.66% brain retrieval accuracy averaged over four subjects, surpassing the state-of-the-art method by 5.71% brain retrieval accuracy with fewer trainable adaptation parameters. Our code is available at https://github.com/lingeringlight/StableMind.

Problem

• source-free adaptation
• cross-subject fMRI decoding
• brain representation stability
• image supervision reliability
• limited fMRI data

Innovation

• source-free adaptation
• fMRI decoding
• representation stability
• image supervision reliability
• Fourier-based augmentation