Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2509.18481 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914052004904960 |
|---|---|
| author | Wang, Xinyu Zhou, Zikun Li, Yingjian An, Xin Wang, Hongpeng |
| author_facet | Wang, Xinyu Zhou, Zikun Li, Yingjian An, Xin Wang, Hongpeng |
| contents | Coding images for machines with minimal bitrate and strong analysis performance is key to effective edge-cloud systems. Several approaches deploy an image codec and perform analysis on the reconstructed image. Other methods compress intermediate features using entropy models and subsequently perform analysis on the decoded features. Nevertheless, these methods both perform poorly under low-bitrate conditions, as they retain many redundant details or learn over-concentrated symbol distributions. In this paper, we propose a Codebook-based Adaptive Feature Compression framework with Semantic Enhancement, named CAFC-SE. It maps continuous visual features to discrete indices with a codebook at the edge via Vector Quantization (VQ) and selectively transmits them to the cloud. The VQ operation that projects feature vectors onto the nearest visual primitives enables us to preserve more informative visual patterns under low-bitrate conditions. Hence, CAFC-SE is less vulnerable to low-bitrate conditions. Extensive experiments demonstrate the superiority of our method in terms of rate and accuracy. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_18481 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Codebook-Based Adaptive Feature Compression With Semantic Enhancement for Edge-Cloud Systems Wang, Xinyu Zhou, Zikun Li, Yingjian An, Xin Wang, Hongpeng Computer Vision and Pattern Recognition Coding images for machines with minimal bitrate and strong analysis performance is key to effective edge-cloud systems. Several approaches deploy an image codec and perform analysis on the reconstructed image. Other methods compress intermediate features using entropy models and subsequently perform analysis on the decoded features. Nevertheless, these methods both perform poorly under low-bitrate conditions, as they retain many redundant details or learn over-concentrated symbol distributions. In this paper, we propose a Codebook-based Adaptive Feature Compression framework with Semantic Enhancement, named CAFC-SE. It maps continuous visual features to discrete indices with a codebook at the edge via Vector Quantization (VQ) and selectively transmits them to the cloud. The VQ operation that projects feature vectors onto the nearest visual primitives enables us to preserve more informative visual patterns under low-bitrate conditions. Hence, CAFC-SE is less vulnerable to low-bitrate conditions. Extensive experiments demonstrate the superiority of our method in terms of rate and accuracy. |
| title | Codebook-Based Adaptive Feature Compression With Semantic Enhancement for Edge-Cloud Systems |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2509.18481 |