Wills Aligner: A Robust Multi-Subject Brain Representation Learner

arXiv:2404.13282v1 Announce Type: new
Abstract: Decoding visual information from human brain activity has seen remarkable advancements in recent research. However, due to the significant variability in cortical parcellation and cognition patterns across subjects, current approaches personalized deep models for each subject, constraining the practicality of this technology in real-world contexts. To tackle the challenges, we introduce Wills Aligner, a robust multi-subject brain representation learner. Our Wills Aligner initially aligns different subjects' brains at the anatomical level. Subsequently, it incorporates a …

abstract arxiv brain brain activity cognition cs.cv cs.mm current decoding however human information patterns personalized representation research robust technology type visual world