Efficient Multi Subject Visual Reconstruction from fMRI Using Aligned Representations
This addresses the problem of inefficient multi-subject fMRI analysis for researchers, though it appears incremental as it builds on existing representation alignment techniques.
The paper tackles visual image reconstruction from fMRI by aligning brain signals of multiple subjects into a common representation space, showing that aligning lightweight subject-specific modules to a reference subject is more efficient than traditional methods, especially in low-data scenarios.
This work introduces a novel approach to fMRI-based visual image reconstruction using a subject-agnostic common representation space. We show that the brain signals of the subjects can be aligned in this common space during training to form a semantically aligned common brain. This is leveraged to demonstrate that aligning subject-specific lightweight modules to a reference subject is significantly more efficient than traditional end-to-end training methods. Our approach excels in low-data scenarios. We evaluate our methods on different datasets, demonstrating that the common space is subject and dataset-agnostic.