首个支持多任务的分层压缩模型，显著降低边缘设备延迟与能耗。
A Multi-task Supervised Compression Model for Split Computing
- 设计多任务监督压缩架构，早期层学习紧凑表征
- 在多个数据集上性能优于或媲美轻量级基线模型
- 移动端端到端延迟降低95.4%，能耗减少88.2%
分层计算（split computing）是一种适用于资源受限边缘计算系统的深度学习方法，其中弱算力的传感器（如移动设备）通过通信容量有限的信道连接至更强的边缘服务器。现有分层计算研究多针对单一任务（如图像分类、目标检测或语义分割），应用于多任务场景时会降低模型精度或显著增加运行延迟。本文提出Ladon，首个面向多任务分层计算的多头监督压缩模型。实验表明，该模型在ILSVRC 2012、COCO 2017和PASCAL VOC 2012数据集上的预测性能优于或媲美强健的轻量级基线模型，同时在早期层学习压缩表示。此外，在多任务分层计算场景中，模型将移动端端到端延迟降低最高达95.4%，能量消耗减少最高达88.2%。
原文摘要 · Abstract (English)
Split computing ($\neq$ split learning) is a promising approach to deep learning models for resource-constrained edge computing systems, where weak sensor (mobile) devices are wirelessly connected to stronger edge servers through channels with limited communication capacity. State-of-theart work on split computing presents methods for single tasks such as image classification, object detection, or semantic segmentation. The application of existing methods to multitask problems degrades model accuracy and/or significantly increase runtime latency. In this study, we propose Ladon, the first multi-task-head supervised compression model for multi-task split computing. Experimental results show that the multi-task supervised compression model either outperformed or rivaled strong lightweight baseline models in terms of predictive performance for ILSVRC 2012, COCO 2017, and PASCAL VOC 2012 datasets while learning compressed representations at its early layers. Furthermore, our models reduced end-to-end latency (by up to 95.4%) and energy consumption of mobile devices (by up to 88.2%) in multi-task split computing scenarios.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。