Skip to content

FlatClip: A Geometry-Aware Surface-Level Baseline for fMRI Representation Learning

Sep 2026 · arXiv.org · Vol abs/2609.31204 · 0 citations · 38 references
Computer Science

TL;DR

FlatClip is introduced, a frozen-encoder surface-level baseline that renders cortical activity as geometry-aware flatmap sequences and reuses a frozen SigLIP2 image encoder with only a lightweight downstream probe, and support the utility of anatomy-linked spatial organization for reusing image-pretrained features.

Abstract

Recent fMRI foundation models differ substantially in the spatial scale at which they represent brain activity. ROI- and connectivity-based models are efficient but coarse, whereas voxel-level models preserve fine-grained spatial structure but require specialized 3D/4D architectures and costly fMRI-specific pretraining. We ask how effectively an image-pretrained encoder can reuse the spatial organization of cortical activity. Motivated by evidence that macroscale brain activity is strongly constrained by brain geometry, we introduce FlatClip, a frozen-encoder surface-level baseline that renders cortical activity as geometry-aware flatmap sequences and reuses a frozen SigLIP2 image encoder with only a lightweight downstream probe. Across resting-state benchmarks, FlatClip serves as a competitive middle-ground representation, outperforming ROI-level baselines on HCP and ADNI tasks while remaining weaker on PPMI and below the strongest voxel-level models overall. On visual-fMRI decoding, restricting the input to visual or NSD-provided task-active cortex improves performance, highlighting the value of task-relevant cortical coverage. Spatial perturbation controls reduce the predictive performance of flatmap features under both retrained and fixed readouts, and anatomy-linked arrangements consistently outperform vertex permutations across three colormaps. Together, these results position surface-level flatmap sequences as a practical middle-ground baseline between ROI and voxel models, and support the utility of anatomy-linked spatial organization for reusing image-pretrained features. Code is available at https://github.com/OneMore1/FlatClip.

View source

Similar papers

#artificial intelligence Review Sep 2026

A Roadmap for MEG Foundation Models

This perspective lays down the basic concepts needed to understand MEG foundation models and provides a didactic overview of the field's key design choices, including tokenization, sensor- versus source-space representations, sensor-geometry encoding, backbone architectures, self-supervised objectives, and pretraining...

Philipp Thölke, Hamza Abdelhedi, Yorguin-José Mantilla-Ramos et al. · 1 citation
Sep 2026

Reduce, Then Encode: Multiscale Volumetric Reduction for 2D Foundation Models in Brain MRI

Multiscale Volumetric Reduction (MVR), a reduce-then-encode approach that compresses each anatomical view from (D) slices into (M<<D) complementary 2D components before foundation-model encoding, achieves strong overall performance across ADNI, OASIS, and ABIDE relative to the evaluated 2D-to-3D adaptation methods and...

De-Xuan Ding, Yuan-Kai Qi, Bo-Gong Wang et al. · 0 citations

Flattening the Connectome Spectrum: A Spectral Filter for FC Induces a Pretraining Target for fMRI Encoders

It is shown that KRR is weighted by the eigenvalues of the FC which are miscalibrated for phenotype prediction, and an efficient spectral filter is applied to recalibrate the eigenvalues of each subject's FC matrix, enabling the model to exploit more inter-individual variance.

G. Marraffini, Victoria Shevchenko, Carlo Alberto Barbano et al. · 0 citations
Open access Sep 2026

DeID-Aligner: Fine-Grained Brain-Vision Semantic Alignment for Cross-Subject Visual Decoding from Limited fMRI Data.

Recent advances in fMRI-based semantic decoding and visual reconstruction have achieved remarkable progress. However, severe inter-subject variability and the scarcity of paired fMRI-image data remain major obstacles to cross-subject generalization. To overcome these challenges, we propose DeID-Aligner, a brain functio...

Xu Yin, John Q. Gan, Ming Yang et al. · 0 citations
#machine learning Preprint Sep 2026

FAST-Brain: A Flow-Aligned Spatio-Temporal Surrogate Brain Model

FAST-Brain is proposed, a unified flow-aligned spatio-temporal surrogate brain model that addresses all three challenges of resting-state functional magnetic resonance imaging data, and achieves state-of-the-art performance in recovering functional connectivity, effective connectivity, and the implicit low-dimensional...

Shu-Cheng Liu, Chang-Chun Shi, Kai Zhang et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.