EdgeFM: Leveraging Foundation Model for Open-set Learning on the Edge
This work addresses the problem of improving generalization and efficiency for deep learning on IoT devices, representing an incremental advancement in edge-cloud systems.
The paper tackles the challenge of deploying foundation models on resource-limited edge devices by proposing EdgeFM, an edge-cloud cooperative system that achieves up to 3.2x reduction in end-to-end latency and a 34.3% accuracy increase compared to baselines.
Deep Learning (DL) models have been widely deployed on IoT devices with the help of advancements in DL algorithms and chips. However, the limited resources of edge devices make these on-device DL models hard to be generalizable to diverse environments and tasks. Although the recently emerged foundation models (FMs) show impressive generalization power, how to effectively leverage the rich knowledge of FMs on resource-limited edge devices is still not explored. In this paper, we propose EdgeFM, a novel edge-cloud cooperative system with open-set recognition capability. EdgeFM selectively uploads unlabeled data to query the FM on the cloud and customizes the specific knowledge and architectures for edge models. Meanwhile, EdgeFM conducts dynamic model switching at run-time taking into account both data uncertainty and dynamic network variations, which ensures the accuracy always close to the original FM. We implement EdgeFM using two FMs on two edge platforms. We evaluate EdgeFM on three public datasets and two self-collected datasets. Results show that EdgeFM can reduce the end-to-end latency up to 3.2x and achieve 34.3% accuracy increase compared with the baseline.