标签
This paper proposes OSPDIM, a source-free online unsupervised domain adaptation framework for EEG-based BCIs that corrects geometric misalignment caused by class-imbalanced label shifts on the Riemannian manifold, outperforming standard alignment methods in online scenarios.
本文提出了一种局部感知的私有类识别方法，以及一种基于可靠最优传输的方法（ReOT），以解决极端标签偏移下的域适应挑战，特别是区分共享类与私有类。