Shoggoth: Towards Efficient Edge-Cloud Collaborative Real-Time Video Inference via Adaptive Online Learning

This paper proposes Shoggoth, an efficient edge-cloud collaborative architecture, for boosting inference performance on real-time video of changing scenes. Shoggoth uses online knowledge distillation to improve the accuracy of models suffering from data drift and offloads the labeling process to the...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:2023 60th ACM/IEEE Design Automation Conference (DAC) s. 1 - 6
Hlavní autoři: Wang, Liang, Lu, Kai, Zhang, Nan, Qu, Xiaoyang, Wang, Jianzong, Wan, Jiguang, Li, Guokuan, Xiao, Jing
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 09.07.2023
Témata:
Adaptation models
Bandwidth
Collaboration
Computational modeling
Computer architecture
Streaming media
Training
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:This paper proposes Shoggoth, an efficient edge-cloud collaborative architecture, for boosting inference performance on real-time video of changing scenes. Shoggoth uses online knowledge distillation to improve the accuracy of models suffering from data drift and offloads the labeling process to the cloud, alleviating constrained resources of edge devices. At the edge, we design adaptive training using small batches to adapt models under limited computing power, and adaptive sampling of training frames for robustness and reducing bandwidth. The evaluations on the realistic dataset show 15%-20% model accuracy improvement compared to the edge-only strategy and fewer network costs than the cloud-only strategy.
DOI:10.1109/DAC56929.2023.10247821