Feature Compression for Machines with Range-Based Channel Truncation and Frame Packing
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_ | 1866918245575950336 |
|---|---|
| author | Merlos, Juan Racapé, Fabien Choi, Hyomin Ulhaq, Mateen Kalva, Hari |
| author_facet | Merlos, Juan Racapé, Fabien Choi, Hyomin Ulhaq, Mateen Kalva, Hari |
| contents | This paper proposes a method that enhances the compression performance of the current model under development for the upcoming MPEG standard on Feature Coding for Machines (FCM). This standard aims at providing inter-operable compressed bitstreams of features in the context of split computing, i.e., when the inference of a large computer vision neural-network (NN)-based model is split between two devices. Intermediate features can consist of multiple 3D tensors that can be reduced and entropy coded to limit the required bandwidth of such transmission. In the envisioned design for the MPEG-FCM standard, intermediate feature tensors may be reduced using Neural layers before being converted into 2D video frames that can be coded using existing video compression standards. This paper introduces an additional channel truncation and packing method which enables the system to preserve the relevant channels, depending on the statistics of the features at inference time, while preserving the computer vision task performance at the receiver. Implemented within the MPEG-FCM test model, the proposed method yields an average reduction in rate by 10.59% for a given accuracy on multiple computer vision tasks and datasets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_11134 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Feature Compression for Machines with Range-Based Channel Truncation and Frame Packing Merlos, Juan Racapé, Fabien Choi, Hyomin Ulhaq, Mateen Kalva, Hari Image and Video Processing This paper proposes a method that enhances the compression performance of the current model under development for the upcoming MPEG standard on Feature Coding for Machines (FCM). This standard aims at providing inter-operable compressed bitstreams of features in the context of split computing, i.e., when the inference of a large computer vision neural-network (NN)-based model is split between two devices. Intermediate features can consist of multiple 3D tensors that can be reduced and entropy coded to limit the required bandwidth of such transmission. In the envisioned design for the MPEG-FCM standard, intermediate feature tensors may be reduced using Neural layers before being converted into 2D video frames that can be coded using existing video compression standards. This paper introduces an additional channel truncation and packing method which enables the system to preserve the relevant channels, depending on the statistics of the features at inference time, while preserving the computer vision task performance at the receiver. Implemented within the MPEG-FCM test model, the proposed method yields an average reduction in rate by 10.59% for a given accuracy on multiple computer vision tasks and datasets. |
| title | Feature Compression for Machines with Range-Based Channel Truncation and Frame Packing |
| topic | Image and Video Processing |
| url | https://arxiv.org/abs/2512.11134 |