GraViT: Transfer Learning with Vision Transformers and MLP-Mixer for Strong Gravitational Lens Discovery
| Notebook | Description |
|---|---|
| a1-C21-classification-head.ipynb | Fine-tune only the classification head |
| a2-C21-half.ipynb | Fine-tune half of the layers |
| a3-C21-all-blocks+ResNet18.ipynb | Train all layers + ResNet18 baseline |
| Notebook | Description |
|---|---|
| b1-J24-classification-head.ipynb | Fine-tune only the classification head |
| b2-J24-half.ipynb | Fine-tune half of the layers |
| b3-J24-all-blocks.ipynb | Train all layers |
| Notebook | Description |
|---|---|
| c1-C21+J24-classification-head.ipynb | Fine-tune only the classification head |
| c2-C21+J24-half.ipynb | Fine-tune half of the layers |
| c3-C21+J24-all-blocks+ResNet18.ipynb | Train all transformer blocks + ResNet18 baseline |
| Notebook | Description |
|---|---|
| s1-C21-18660-classification-head.ipynb | Fine-tune only the classification head |
| s2-C21-18660-half.ipynb | Fine-tune half of the layers |
| s3-C21-18660-all-blocks+ResNet18.ipynb | Train all layers + ResNet18 baseline |
| Notebook | Description |
|---|---|
| inference-L2.ipynb | Recall for search in L2 subset (138 lenses) |
Figure 1: Vision Transformer (ViT) architecture for strong gravitational lens detection.
Figure 2: MLP-Mixer architecture for strong gravitational lens detection.
| Resource | Link |
|---|---|
| 🤗 Models (Hugging Face) | https://huggingface.co/collections/parlange/gravit |
| 📦 Models (Zenodo) | https://zenodo.org/records/16897575 |
If you use this work in your research, please cite:
@article{10.1093/mnras/staf1747,
author = {Parlange, René and Cuevas-Tello, Juan C and Valenzuela, Octavio and Cabrera-Rosas, Omar de J and Verdugo, Tomás and More, Anupreeta and Jaelani, Anton T},
title = {GraViT: transfer learning with vision transformers and MLP-Mixer for strong gravitational lens discovery},
journal = {Monthly Notices of the Royal Astronomical Society},
volume = {545},
number = {2},
pages = {staf1747},
year = {2025},
month = {10},
issn = {0035-8711},
doi = {10.1093/mnras/staf1747},
url = {https://doi.org/10.1093/mnras/staf1747},
}