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.

翻译：深度学习模型在算法与芯片进步的推动下已广泛部署于物联网设备。然而，边缘设备资源受限使得这些端侧深度学习模型难以适应多样化的环境与任务。尽管近期涌现的基础模型展现出卓越的泛化能力，但如何有效利用资源受限边缘设备上基础模型的丰富知识仍未得到探索。本文提出EdgeFM——一种具备开放集识别能力的新型端云协作系统。EdgeFM选择性上传未标注数据以查询云端基础模型，并为边缘模型定制特定知识与架构。同时，EdgeFM在运行时根据数据不确定性与动态网络变化进行动态模型切换，确保精度始终接近原始基础模型。我们在两种边缘平台上使用两种基础模型实现EdgeFM，并在三个公开数据集与两个自采集数据集上进行评估。结果表明，与基线相比，EdgeFM可将端到端延迟降低至多3.2倍，并将准确率提升34.3%。