Feature Coding for Scalable Machine Vision

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Eimon, Md Eimran Hossain, Merlos, Juan, Perera, Ashan, Kalva, Hari, Adzic, Velibor, Furht, Borko
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909956557504512
author Eimon, Md Eimran Hossain
Merlos, Juan
Perera, Ashan
Kalva, Hari
Adzic, Velibor
Furht, Borko
author_facet Eimon, Md Eimran Hossain
Merlos, Juan
Perera, Ashan
Kalva, Hari
Adzic, Velibor
Furht, Borko
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2512_10209
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Feature Coding for Scalable Machine Vision
Eimon, Md Eimran Hossain
Merlos, Juan
Perera, Ashan
Kalva, Hari
Adzic, Velibor
Furht, Borko
Computer Vision and Pattern Recognition
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.
title Feature Coding for Scalable Machine Vision
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2512.10209