UniBrain: A Unified Model for Cross-Subject Brain Decoding
This work addresses the challenge of generalizing brain decoding models across individuals, which is crucial for advancing neuroscience and AI applications, though it appears incremental as it builds on existing benchmarks.
The authors tackled the problem of brain decoding from fMRI signals by developing UniBrain, a unified model that eliminates the need for subject-specific parameters, achieving comparable performance to state-of-the-art subject-specific models with significantly fewer parameters.
Brain decoding aims to reconstruct original stimuli from fMRI signals, providing insights into interpreting mental content. Current approaches rely heavily on subject-specific models due to the complex brain processing mechanisms and the variations in fMRI signals across individuals. Therefore, these methods greatly limit the generalization of models and fail to capture cross-subject commonalities. To address this, we present UniBrain, a unified brain decoding model that requires no subject-specific parameters. Our approach includes a group-based extractor to handle variable fMRI signal lengths, a mutual assistance embedder to capture cross-subject commonalities, and a bilevel feature alignment scheme for extracting subject-invariant features. We validate our UniBrain on the brain decoding benchmark, achieving comparable performance to current state-of-the-art subject-specific models with extremely fewer parameters. We also propose a generalization benchmark to encourage the community to emphasize cross-subject commonalities for more general brain decoding. Our code is available at https://github.com/xiaoyao3302/UniBrain.