braindecode/eegdino-small-pretrained

EEG-DINO Small — Self-Distillation EEG Foundation Model

EEG-DINO-Small encoder pretrained with DINO-v2 hierarchical self-distillation (Wang et al., MICCAI 2025).

This is the eegdino-small-pretrained checkpoint for braindecode.models.EEGDINO, curated and re-uploaded as part of the OpenEEG-Bench effort.

Quick start

pip install braindecode[hub]

from braindecode.models import EEGDINO

model = EEGDINO.from_pretrained(
    "braindecode/eegdino-small-pretrained",
    n_outputs=2,            # set to your downstream task
    n_chans=19,
    sfreq=200,
)

from_pretrained reads both the architecture configuration (config.json) and the weights (model.safetensors or pytorch_model.bin) and returns a ready-to-fine-tune nn.Module.

Model details

Architecture	braindecode.models.EEGDINO
Expected channels	19
Expected sampling frequency	200 Hz
Library	braindecode ≥ 1.5
Loaded via	huggingface_hub.PyTorchModelHubMixin (free with braindecode[hub])

For the full architecture description, parameter table, and references, see the rendered docstring at https://braindecode.org/stable/generated/braindecode.models.EEGDINO.html or in the interactive Model Explorer Space.

Training data

Temple University Hospital EEG Corpus (TUEG), 19 common 10-20 channels resampled to 200 Hz (>9000 hours), following CBraMod's preprocessing. Pretrained by hierarchical self-distillation.

Intended use

EEG feature extraction or fine-tuning for downstream classification (e.g., TUEV, TUAB). The classification head is re-initialized on load; fine-tune or linear-probe before use.

Limitations

• Channel layout matters. Performance degrades when the input montage differs from the pretraining montage. Use the Interpolated* variant (where available) or resample channels with MNE before fine-tuning.
• Sampling rate matters. Resample your data to 200 Hz before inference; the positional / patch embeddings assume this rate.
• Inherited license restrictions. Downstream weights derived from this checkpoint inherit the license of the original training corpus (some braindecode pretraining corpora are CC-BY-NC). Verify the upstream dataset licence before commercial use.

Citation

If you use this checkpoint, please cite both the original architecture paper and braindecode.

@inproceedings{wang2025eegdino,
  title     = {{EEG-DINO}: Learning {EEG} Foundation Models via Hierarchical
               Self-Distillation},
  author    = {Wang, Xujia and Liu, Xuhui and Liu, Xi and Si, Qian and Xu,
               Zhaoliang and Li, Yang and Zhen, Xiantong},
  booktitle = {Medical Image Computing and Computer Assisted Intervention (MICCAI)},
  year      = {2025},
}

@article{aristimunha2025braindecode,
  title   = {Braindecode: a deep learning library for raw electrophysiological data},
  author  = {Aristimunha, Bruno and others},
  journal = {Zenodo},
  year    = {2025},
  doi     = {10.5281/zenodo.17699192},
}

License

BSD-3-Clause for the model code (matching braindecode). The pretraining data may impose additional restrictions — see Limitations.