Structure invariance-driven collaborative contrastive network for EEG decoding

Shuang Liang, Zengguang Li, Wenlong Hang, Yuanpeng Zhang 0004, Baiying Lei, Jing Qin, Yu Zhang 0009, Kup-Sze Choi

Abstract

Highlights•Novel structure invariance-driven collaborative contrastive network (SICCNet) for EEG decoding.•Novel EEG DA method linearly interpolates the segments of the same class data to alleviate the undesirable noise.•SICCNet learns the invariant data-structure information across augmented views to enhance the generalizability of the model.
BibTeX
@article{liang2023structure,
  author = {Shuang Liang and Zengguang Li and Wenlong Hang and Yuanpeng Zhang and Baiying Lei and Jing Qin and Yu Zhang and Kup-Sze Choi},
  title = {{Structure invariance-driven collaborative contrastive network for EEG decoding}},
  journal = {Biomedical Signal Processing and Control},
  year = {2023},
  doi = {10.1016/j.bspc.2023.105214},
}

Loading related content...

Figure