Efficient onboard multi-task AI architecture based on self-supervised learning

TL;DR

This paper introduces a modular, lightweight self-supervised AI architecture for onboard satellite inference, enabling multiple tasks with high efficiency and minimal data labeling, suitable for real-time critical event analysis.

Contribution

It proposes a novel self-supervised backbone and task-specific heads for efficient, multi-task onboard satellite AI with reduced data labeling needs.

Findings

Achieves inference quality close to state-of-the-art models

Runs at over 8 million pixels per second on a 7W embedded system

Demonstrates effectiveness on cloud segmentation, flood detection, and debris classification

Abstract

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.