README.md

---
license: bsd-3-clause
library_name: braindecode
pipeline_tag: feature-extraction
tags:
  - eeg
  - biosignal
  - pytorch
  - neuroscience
  - eeg-dino
  - foundation-model
  - self-supervised
  - self-distillation
  - braindecode
  - model_hub_mixin
  - pytorch_model_hub_mixin
---

# EEG-DINO Medium — Self-Distillation EEG Foundation Model

EEG-DINO-Medium encoder (~33M parameters) pretrained with DINO-v2 hierarchical self-distillation (Wang et al., MICCAI 2025).

This is the **eegdino-medium-pretrained** checkpoint for `braindecode.models.EEGDINO`,
curated and re-uploaded as part of the
[OpenEEG-Bench](https://huggingface.co/spaces/braindecode/OpenEEGBench) effort.

## Quick start

```bash
pip install braindecode[hub]
```

```python
from braindecode.models import EEGDINO

model = EEGDINO.from_pretrained(
    "braindecode/eegdino-medium-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](https://github.com/braindecode/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](https://huggingface.co/spaces/braindecode/model-explorer).

## 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

Larger EEG-DINO encoder for feature extraction or fine-tuning; the architecture is restored from config.json on load. The classification head is re-initialized on load.

## 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.

```bibtex
@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*.