You Only Look Once, But Compute Twice: Service Function Chaining for Low-Latency Object Detection in Softwarized Networks

Abstract

With increasing numbers of computer vision and object detection application scenarios, those requiring ultra-low service latency times have become increasingly prominent; e.g., those for autonomous and connected vehicles or smart city applications. The incorporation of machine learning through the applications of trained models in these scenarios can pose a computational challenge. The softwarization of networks provides opportunities to incorporate computing into the network, increasing flexibility by distributing workloads through offloading from client and edge nodes over in-network nodes to servers. In this article, we present an example for splitting the inference component of the YOLOv2 trained machine learning model between client, network, and service side processing to reduce the overall service latency. Assuming a client has 20% of the server computational resources, we observe a more than 12-fold reduction of service latency when incorporating our service split compared to on-client processing and and an increase in speed of more than 25% compared to performing everything on the server. Our approach is not only applicable to object detection, but can also be applied in a broad variety of machine learning-based applications and services.

Application and Theory of Multimedia Signal Processing Using Machine Learning or Advanced Methods

“…The sixth paper (Xiang et al ( 2021)) [6] is a study of an example for splitting the inference component of the YOLOv2 trained machine learning model between client, network, and service side processing to reduce the overall service latency. The approach of this research is not only applicable to object detection, but can also be applied in a broad variety of machine learning-based applications and services.…”

In-Network Processing Acoustic Data for Anomaly Detection in Smart Factory

“…Existing in-network processing studies focus more on how to embed computing tasks into a network, deriving the processing results closer to the users [12]. For example, the work in [13] decomposes an image detection job as a service function chain. Since the processing can be simply done at closer nodes, it reduces the latency by more than 25%.…”

Fusion Enhancement of YOLOv5 and Copula Bayesian Classifier for Hand Gesture Recognition in Smart Sports Venues

“…Amidst these methodologies, the HGDR-Net algorithm based on YOLO (You Only Look Once) v5 garners attention [25][26][27]. This algorithm initially utilizes the YOLO algorithm for gesture detection and then employs a Convolutional Neural Network (CNN) for gesture classification [14,28].…”