Skip to main navigation Skip to search Skip to main content

Wills aligner: multi-subject collaborative brain visual decoding

  • Guangyin Bao
  • , Qi Zhang
  • , Zixuan Gong
  • , Jialei Zhou
  • , Wei Fan
  • , Kun Yi
  • , Usman Naseem
  • , Liang Hu
  • , Duoqian Miao*
  • *Corresponding author for this work

Research output: Contribution to journal › Conference paper › peer-review

Abstract

Decoding visual information from human brain activity has seen remarkable advancements in recent research. However, the diversity in cortical parcellation and fMRI patterns across individuals has prompted the development of deep learning models tailored to each subject. The personalization limits the broader applicability of brain visual decoding in real-world scenarios. To address this issue, we introduce Wills Aligner, a novel approach designed to achieve multi-subject collaborative brain visual decoding. Wills Aligner begins by aligning the fMRI data from different subjects at the anatomical level. It then employs delicate mixture-of-brain-expert adapters and a meta-learning strategy to account for individual fMRI pattern differences. Additionally, Wills Aligner leverages the semantic relation of visual stimuli to guide the learning of intersubject commonality, enabling visual decoding for each subject to draw insights from other subjects' data. We rigorously evaluate our Wills Aligner across various visual decoding tasks, including classification, cross-modal retrieval, and image reconstruction. The experimental results demonstrate that Wills Aligner achieves promising performance.
Original languageEnglish
Pages (from-to)14194-14202
Number of pages9
JournalProceedings of the AAAI Conference on Artificial Intelligence
Volume39
Issue number13
DOIs
Publication statusPublished - 2025
Event39th AAAI Conference on Artificial Intelligence - Philadelphia, Panama
Duration: 25 Feb 2025 → 4 Mar 2025

Bibliographical note

ISBN-10: 1-57735-897-X
ISBN-13: 978-1-57735-897-8

Fingerprint

Dive into the research topics of 'Wills aligner: multi-subject collaborative brain visual decoding'. Together they form a unique fingerprint.

Cite this