FlatClip is introduced, which renders cortical activity as anatomy-linked flatmaps and extracts features with a frozen SigLIP2 encoder, which demonstrates a practical route for reusing image-pretrained features in fMRI and highlights cortical arrangement and input-region selection as important design choices.
Mo Wang, Wen-Hao Ye, Zi-Han Ning et al.· 0 citations
Functional magnetic resonance imaging (fMRI) commonly characterizes large-scale brain organization through functional connectivity (FC). However, an observed FC matrix is not a fixed brain graph but a statistical estimate determined by the finite BOLD frames used to compute it. Conventional FC-based approaches typicall...
Zi-Teng Sui, Jun-Feng Xia, Wen-Hao Ye et al.· 0 citations
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.
Mo Wang, Wen-Hao Ye, Zi-Han Ning et al.· arXiv.org· 0 citations
Overall, the results show that compute alone does not characterize fMRI scaling: performance depends on how pretraining data, model size, and training duration are combined.
Wen-Hao Ye, Xuan-Ye Pan, Jun-Feng Xia 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.