用压缩中间特征提升边缘视觉模型部署效率
Feature Coding for Scalable Machine Vision
- 设计专用编码器压缩神经网络中间特征
- 多任务平均压缩率达85.14%且保持准确率
- 适合对带宽和隐私敏感的智能设备应用
深度神经网络驱动现代机器视觉，但因计算需求高难以部署在边缘设备。传统方案——在设备上运行完整模型或云端推理，分别面临延迟、带宽与隐私的权衡。将推理任务分摊至边缘与云端可平衡性能，但传输中间特征会引入新的带宽挑战。为此，运动图像专家组（MPEG）启动了面向机器的特征编码（FCM）标准，建立了专为压缩中间特征设计的比特流语法与编解码流程。本文介绍了特征编码测试模型（FCTM）的设计与性能表现，在多个视觉任务中平均比特率降低85.14%，同时保持精度。FCM为带宽受限且注重隐私的消费级应用提供了高效、可互操作的智能特征部署路径。
原文摘要 · Abstract (English)
Deep neural networks (DNNs) drive modern machine vision but are challenging to deploy on edge devices due to high compute demands. Traditional approaches-running the full model on-device or offloading to the cloud face trade-offs in latency, bandwidth, and privacy. Splitting the inference workload between the edge and the cloud offers a balanced solution, but transmitting intermediate features to enable such splitting introduces new bandwidth challenges. To address this, the Moving Picture Experts Group (MPEG) initiated the Feature Coding for Machines (FCM) standard, establishing a bitstream syntax and codec pipeline tailored for compressing intermediate features. This paper presents the design and performance of the Feature Coding Test Model (FCTM), showing significant bitrate reductions-averaging 85.14%-across multiple vision tasks while preserving accuracy. FCM offers a scalable path for efficient and interoperable deployment of intelligent features in bandwidth-limited and privacy-sensitive consumer applications.
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。