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

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.

References in corpus (7)

• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• Distilling the Knowledge in a Neural Network
• Rethinking Atrous Convolution for Semantic Image Segmentation
• High-Resolution Representations for Labeling Pixels and Regions
• GhostNetV2: Enhance Cheap Operation with Long-Range Attention
• Foundational Models Defining a New Era in Vision: A Survey and Outlook
• Semi-supervised learning for joint SAR and multispectral land cover classification