Said, NainaNainaSaidLandsiedel, OlafOlafLandsiedel2025-02-042025-02-042024-0420th International Conference on Distributed Computing in Smart Systems and the Internet of Things (DCOSS-IoT) 2024979-8-3503-6944-1979-8-3503-6945-8https://hdl.handle.net/11420/53823This paper introduces EdgeBoost, a selective input offloading system designed to overcome the challenges of limited computational resources on edge devices. EdgeBoost trains and calibrates a lightweight model for deployment on the edge and, in addition, deploys a large, complex model on the cloud. During inference, the edge model makes initial predictions for input samples, and if the confidence of the prediction is low, the sample is sent to the cloud model for further processing otherwise, we accept the local prediction. Due to careful calibration, EdgeBoost reduces the communication cost by 55%, 29% and 20% for CIFAR-100, ImageNet and Stanford Cars datasets, respectively, when compared to an cloud-only solution while achieving on par classification accuracy. Finally, EdgeBoost also achieves comparable accuracy to the state-of-the-art routing-based methods without the need for hosting the router on the edge.enInference Offloading | Lightweight Models | MCU | Model Calibration | Temperature Scaling | TinyMLMLE@TUHHTechnology::600: TechnologyConference Paper10.1109/DCOSS-IoT61029.2024.00013Conference Paper