Towards Robust and Efficient Cloud-Edge Elastic Model Adaptation via Selective Entropy Distillation

arXiv:2402.17316v1 Announce Type: new
Abstract: The conventional deep learning paradigm often involves training a deep model on a server and then deploying the model or its distilled ones to resource-limited edge devices. Usually, the models shall remain fixed once deployed (at least for some period) due to the potential high cost of model adaptation for both the server and edge sides. However, in many real-world scenarios, the test environments may change dynamically (known as distribution shifts), which often results in …

abstract arxiv cloud cs.cv deep learning devices distillation edge edge devices elastic entropy least model adaptation paradigm robust server training type via