QuantV2X: A Fully Quantized Multi-Agent System for Cooperative Perception
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_ | 1866914020286529536 |
|---|---|
| author | Zhao, Seth Z. Zhang, Huizhi Li, Zhaowei Peng, Juntong Chui, Anthony Zhou, Zewei Meng, Zonglin Xiang, Hao Huang, Zhiyu Wang, Fujia Tian, Ran Xu, Chenfeng Zhou, Bolei Ma, Jiaqi |
| author_facet | Zhao, Seth Z. Zhang, Huizhi Li, Zhaowei Peng, Juntong Chui, Anthony Zhou, Zewei Meng, Zonglin Xiang, Hao Huang, Zhiyu Wang, Fujia Tian, Ran Xu, Chenfeng Zhou, Bolei Ma, Jiaqi |
| contents | Cooperative perception through Vehicle-to-Everything (V2X) communication offers significant potential for enhancing vehicle perception by mitigating occlusions and expanding the field of view. However, past research has predominantly focused on improving accuracy metrics without addressing the crucial system-level considerations of efficiency, latency, and real-world deployability. Noticeably, most existing systems rely on full-precision models, which incur high computational and transmission costs, making them impractical for real-time operation in resource-constrained environments. In this paper, we introduce \textbf{QuantV2X}, the first fully quantized multi-agent system designed specifically for efficient and scalable deployment of multi-modal, multi-agent V2X cooperative perception. QuantV2X introduces a unified end-to-end quantization strategy across both neural network models and transmitted message representations that simultaneously reduces computational load and transmission bandwidth. Remarkably, despite operating under low-bit constraints, QuantV2X achieves accuracy comparable to full-precision systems. More importantly, when evaluated under deployment-oriented metrics, QuantV2X reduces system-level latency by 3.2$\times$ and achieves a +9.5 improvement in mAP30 over full-precision baselines. Furthermore, QuantV2X scales more effectively, enabling larger and more capable models to fit within strict memory budgets. These results highlight the viability of a fully quantized multi-agent intermediate fusion system for real-world deployment. The system will be publicly released to promote research in this field: https://github.com/ucla-mobility/QuantV2X. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_03704 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | QuantV2X: A Fully Quantized Multi-Agent System for Cooperative Perception Zhao, Seth Z. Zhang, Huizhi Li, Zhaowei Peng, Juntong Chui, Anthony Zhou, Zewei Meng, Zonglin Xiang, Hao Huang, Zhiyu Wang, Fujia Tian, Ran Xu, Chenfeng Zhou, Bolei Ma, Jiaqi Computer Vision and Pattern Recognition Cooperative perception through Vehicle-to-Everything (V2X) communication offers significant potential for enhancing vehicle perception by mitigating occlusions and expanding the field of view. However, past research has predominantly focused on improving accuracy metrics without addressing the crucial system-level considerations of efficiency, latency, and real-world deployability. Noticeably, most existing systems rely on full-precision models, which incur high computational and transmission costs, making them impractical for real-time operation in resource-constrained environments. In this paper, we introduce \textbf{QuantV2X}, the first fully quantized multi-agent system designed specifically for efficient and scalable deployment of multi-modal, multi-agent V2X cooperative perception. QuantV2X introduces a unified end-to-end quantization strategy across both neural network models and transmitted message representations that simultaneously reduces computational load and transmission bandwidth. Remarkably, despite operating under low-bit constraints, QuantV2X achieves accuracy comparable to full-precision systems. More importantly, when evaluated under deployment-oriented metrics, QuantV2X reduces system-level latency by 3.2$\times$ and achieves a +9.5 improvement in mAP30 over full-precision baselines. Furthermore, QuantV2X scales more effectively, enabling larger and more capable models to fit within strict memory budgets. These results highlight the viability of a fully quantized multi-agent intermediate fusion system for real-world deployment. The system will be publicly released to promote research in this field: https://github.com/ucla-mobility/QuantV2X. |
| title | QuantV2X: A Fully Quantized Multi-Agent System for Cooperative Perception |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2509.03704 |