Efficient onboard multi-task AI architecture based on self-supervised learning
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866908458294444032 |
|---|---|
| author | Inzerillo, Gabriele Valsesia, Diego Magli, Enrico |
| author_facet | Inzerillo, Gabriele Valsesia, Diego Magli, Enrico |
| contents | There is growing interest towards the use of AI directly onboard satellites for quick analysis and rapid response to critical events such as natural disasters. This paper presents a blueprint to the mission designer for the development of a modular and efficient deep learning payload to address multiple onboard inference tasks. In particular, we design a self-supervised lightweight backbone that provides features to efficient task-specific heads. The latter can be developed independently and with reduced data labeling requirements thanks to the frozen backbone. Experiments on three sample tasks of cloud segmentation, flood detection, and marine debris classification on a 7W embedded system show competitive results with inference quality close to high-complexity state-of-the-art models and high throughput in excess of 8 Mpx/s. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_09754 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Efficient onboard multi-task AI architecture based on self-supervised learning Inzerillo, Gabriele Valsesia, Diego Magli, Enrico Image and Video Processing There is growing interest towards the use of AI directly onboard satellites for quick analysis and rapid response to critical events such as natural disasters. This paper presents a blueprint to the mission designer for the development of a modular and efficient deep learning payload to address multiple onboard inference tasks. In particular, we design a self-supervised lightweight backbone that provides features to efficient task-specific heads. The latter can be developed independently and with reduced data labeling requirements thanks to the frozen backbone. Experiments on three sample tasks of cloud segmentation, flood detection, and marine debris classification on a 7W embedded system show competitive results with inference quality close to high-complexity state-of-the-art models and high throughput in excess of 8 Mpx/s. |
| title | Efficient onboard multi-task AI architecture based on self-supervised learning |
| topic | Image and Video Processing |
| url | https://arxiv.org/abs/2408.09754 |