Pruned encoding models for visual cortex fMRI use as few as 1% of neural features per layer without losing accuracy, and different pretrained backbones predict the BOLD signal via distinct visual features.
From voxels to pixels and back: Self-supervision in natural-image reconstruction from fMRI
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
q-bio.NC 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
BOLDreams: Dreaming with pruned in-silico fMRI Encoding Models of the Visual Cortex
Pruned encoding models for visual cortex fMRI use as few as 1% of neural features per layer without losing accuracy, and different pretrained backbones predict the BOLD signal via distinct visual features.