Feature Coding for Scalable Machine Vision
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| 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 |