Feature Coding for Scalable Machine Vision

Deep neural networks drive modern machine vision but are challenging to deploy on edge devices because of their high compute demands. Traditional approaches-running the full model on device or offloading to the cloud-face tradeoffs 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, MPEG initiated the Feature Coding for Machines (FCM) standard, establishing a bitstream syntax and codec pipeline tailored for compressing intermediate features. This article presents the design and performance of the Feature Coding Test Model, showing significant bit-rate 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.