GraViT: Transfer Learning with Vision Transformers and MLP-Mixer for Strong Gravitational Lens Discovery
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914014369415168 |
|---|---|
| author | Parlange, René Cuevas-Tello, Juan C. Valenzuela, Octavio Cabrera-Rosas, Omar de J. Verdugo, Tomás More, Anupreeta Jaelani, Anton T. |
| author_facet | Parlange, René Cuevas-Tello, Juan C. Valenzuela, Octavio Cabrera-Rosas, Omar de J. Verdugo, Tomás More, Anupreeta Jaelani, Anton T. |
| contents | Gravitational lensing offers a powerful probe into the properties of dark matter and is crucial to infer cosmological parameters. The Legacy Survey of Space and Time (LSST) is predicted to find O(10^5) gravitational lenses over the next decade, demanding automated classifiers. In this work, we introduce GraViT, a PyTorch pipeline for gravitational lens detection that leverages extensive pretraining of state-of-the-art Vision Transformer (ViT) models and MLP-Mixer. We assess the impact of transfer learning on classification performance by examining data quality (source and sample size), model architecture (selection and fine-tuning), training strategies (augmentation, normalization, and optimization), and ensemble predictions. This study reproduces the experiments in a previous systematic comparison of neural networks and provides insights into the detectability of strong gravitational lenses on that common test sample. We fine-tune ten architectures using datasets from HOLISMOKES VI and SuGOHI X, and benchmark them against convolutional baselines, discussing complexity and inference-time analysis. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_00226 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | GraViT: Transfer Learning with Vision Transformers and MLP-Mixer for Strong Gravitational Lens Discovery Parlange, René Cuevas-Tello, Juan C. Valenzuela, Octavio Cabrera-Rosas, Omar de J. Verdugo, Tomás More, Anupreeta Jaelani, Anton T. Computer Vision and Pattern Recognition Astrophysics of Galaxies Gravitational lensing offers a powerful probe into the properties of dark matter and is crucial to infer cosmological parameters. The Legacy Survey of Space and Time (LSST) is predicted to find O(10^5) gravitational lenses over the next decade, demanding automated classifiers. In this work, we introduce GraViT, a PyTorch pipeline for gravitational lens detection that leverages extensive pretraining of state-of-the-art Vision Transformer (ViT) models and MLP-Mixer. We assess the impact of transfer learning on classification performance by examining data quality (source and sample size), model architecture (selection and fine-tuning), training strategies (augmentation, normalization, and optimization), and ensemble predictions. This study reproduces the experiments in a previous systematic comparison of neural networks and provides insights into the detectability of strong gravitational lenses on that common test sample. We fine-tune ten architectures using datasets from HOLISMOKES VI and SuGOHI X, and benchmark them against convolutional baselines, discussing complexity and inference-time analysis. |
| title | GraViT: Transfer Learning with Vision Transformers and MLP-Mixer for Strong Gravitational Lens Discovery |
| topic | Computer Vision and Pattern Recognition Astrophysics of Galaxies |
| url | https://arxiv.org/abs/2509.00226 |