StableMind achieves source-free cross-subject fMRI decoding via ridge-projection priors, Fourier brain augmentation, and difficulty-aware image blur, reaching 84.02% image and 81.66% brain retrieval accuracy on the Natural Scenes Dataset with a 5.71% gain over SOTA under 1-hour adaptation.
Dream: Visual decoding from reversing human visual system
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
StableMind: Source-Free Cross-Subject fMRI Decoding with Regularized Adaptation
StableMind achieves source-free cross-subject fMRI decoding via ridge-projection priors, Fourier brain augmentation, and difficulty-aware image blur, reaching 84.02% image and 81.66% brain retrieval accuracy on the Natural Scenes Dataset with a 5.71% gain over SOTA under 1-hour adaptation.