An UltraMNIST classification benchmark to train CNNs for very large images
Abstract Current convolutional neural networks (CNNs) are not designed for large scientific images with rich multi-scale features, such as in satellite and microscopy domain. A new phase of development of CNNs especially designed for large images is awaited. However, application-independent high-qua...
Guardado en:
| Autores principales: | , , , , , , , , |
|---|---|
| Formato: | Artigo |
| Lenguaje: | Inglês |
| Publicado: |
Nature Portfolio
2024-07-01
|
| Colección: | Scientific Data |
| Acceso en línea: | https://doi.org/10.1038/s41597-024-03587-4 |
| Etiquetas: |
Sin Etiquetas, Sea el primero en etiquetar este registro!
|