[Submitted on 25 Sep 2026 (v1), last revised 15 Oct 2026 (this version, v2)]
Abstract:Can the spatial organization of cortical activity help transfer frozen image representations to fMRI prediction? We introduce FlatClip, which renders cortical activity as anatomy-linked flatmaps and extracts features with a frozen SigLIP2 encoder. Only a lightweight downstream probe is trained, without fMRI-specific encoder pretraining or fine-tuning. Across four resting-state benchmarks, FlatClip outperforms the evaluated ROI-level baselines on HCP and ADNI, but is weaker on PPMI and below the strongest voxel-level models overall. On NSD visual-fMRI decoding, restricting inputs to visual or NSD-provided task-active cortex improves recognition over whole-cortex inputs. Spatial perturbations reduce performance with both retrained and fixed readouts, and anatomy-linked arrangements outperform cortical-pixel permutations across three colormaps. Together, these results demonstrate a practical route for reusing image-pretrained features in fMRI and highlight cortical arrangement and input-region selection as important design choices. Code is available at this https URL.
Submission history
From: Mo Wang [view email]
[v1] Fri, 25 Sep 2026 12:42:40 UTC (794 KB)
[v2] Thu, 15 Oct 2026 13:02:44 UTC (1,862 KB)
