Think before You Leap: Content-Aware Low-Cost Edge-Assisted Video Semantic Segmentation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910385601249280 |
|---|---|
| author | Yan, Mingxuan Wang, Yi Xiao, Xuedou Luo, Zhiqing He, Jianhua Wang, Wei |
| author_facet | Yan, Mingxuan Wang, Yi Xiao, Xuedou Luo, Zhiqing He, Jianhua Wang, Wei |
| contents | Offloading computing to edge servers is a promising solution to support growing video understanding applications at resource-constrained IoT devices. Recent efforts have been made to enhance the scalability of such systems by reducing inference costs on edge servers. However, existing research is not directly applicable to pixel-level vision tasks such as video semantic segmentation (VSS), partly due to the fluctuating VSS accuracy and segment bitrate caused by the dynamic video content. In response, we present Penance, a new edge inference cost reduction framework. By exploiting softmax outputs of VSS models and the prediction mechanism of H.264/AVC codecs, Penance optimizes model selection and compression settings to minimize the inference cost while meeting the required accuracy within the available bandwidth constraints. We implement Penance in a commercial IoT device with only CPUs. Experimental results show that Penance consumes a negligible 6.8% more computation resources than the optimal strategy while satisfying accuracy and bandwidth constraints with a low failure rate. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_14326 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Think before You Leap: Content-Aware Low-Cost Edge-Assisted Video Semantic Segmentation Yan, Mingxuan Wang, Yi Xiao, Xuedou Luo, Zhiqing He, Jianhua Wang, Wei Multimedia Offloading computing to edge servers is a promising solution to support growing video understanding applications at resource-constrained IoT devices. Recent efforts have been made to enhance the scalability of such systems by reducing inference costs on edge servers. However, existing research is not directly applicable to pixel-level vision tasks such as video semantic segmentation (VSS), partly due to the fluctuating VSS accuracy and segment bitrate caused by the dynamic video content. In response, we present Penance, a new edge inference cost reduction framework. By exploiting softmax outputs of VSS models and the prediction mechanism of H.264/AVC codecs, Penance optimizes model selection and compression settings to minimize the inference cost while meeting the required accuracy within the available bandwidth constraints. We implement Penance in a commercial IoT device with only CPUs. Experimental results show that Penance consumes a negligible 6.8% more computation resources than the optimal strategy while satisfying accuracy and bandwidth constraints with a low failure rate. |
| title | Think before You Leap: Content-Aware Low-Cost Edge-Assisted Video Semantic Segmentation |
| topic | Multimedia |
| url | https://arxiv.org/abs/2402.14326 |