CVJun 18, 2024

The Wisdom of a Crowd of Brains: A Universal Brain Encoder

arXiv:2406.12179v314 citations
Originality Highly original
AI Analysis

This addresses a bottleneck in neuroscience research and practical applications by enabling more scalable and generalizable brain-encoding models.

The paper tackles the problem of limited training data in image-to-fMRI encoding by proposing a Universal Brain-Encoder that can be trained jointly on data from multiple subjects, datasets, and machines, achieving improved brain-encoding and effective transfer-learning with few examples.

Image-to-fMRI encoding is important for both neuroscience research and practical applications. However, such "Brain-Encoders" have been typically trained per-subject and per fMRI-dataset, thus restricted to very limited training data. In this paper we propose a Universal Brain-Encoder, which can be trained jointly on data from many different subjects/datasets/machines. What makes this possible is our new voxel-centric Encoder architecture, which learns a unique "voxel-embedding" per brain-voxel. Our Encoder trains to predict the response of each brain-voxel on every image, by directly computing the cross-attention between the brain-voxel embedding and multi-level deep image features. This voxel-centric architecture allows the functional role of each brain-voxel to naturally emerge from the voxel-image cross-attention. We show the power of this approach to (i) combine data from multiple different subjects (a "Crowd of Brains") to improve each individual brain-encoding, (ii) quick & effective Transfer-Learning across subjects, datasets, and machines (e.g., 3-Tesla, 7-Tesla), with few training examples, and (iii) use the learned voxel-embeddings as a powerful tool to explore brain functionality (e.g., what is encoded where in the brain).

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes