MACP: Efficient Model Adaptation for Cooperative Perception

• URL: http://arxiv.org/abs/2310.16870v2
• Date: Tue, 7 Nov 2023 05:42:48 GMT
• Title: MACP: Efficient Model Adaptation for Cooperative Perception
• Authors: Yunsheng Ma and Juanwu Lu and Can Cui and Sicheng Zhao and Xu Cao and Wenqian Ye and Ziran Wang
• Abstract summary: We propose a new framework termed MACP, which equips a single-agent pre-trained model with cooperation capabilities. We demonstrate in experiments that the proposed framework can effectively utilize cooperative observations and outperform other state-of-the-art approaches.
• Score: 23.308578463976804
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Vehicle-to-vehicle (V2V) communications have greatly enhanced the perception capabilities of connected and automated vehicles (CAVs) by enabling information sharing to "see through the occlusions", resulting in significant performance improvements. However, developing and training complex multi-agent perception models from scratch can be expensive and unnecessary when existing single-agent models show remarkable generalization capabilities. In this paper, we propose a new framework termed MACP, which equips a single-agent pre-trained model with cooperation capabilities. We approach this objective by identifying the key challenges of shifting from single-agent to cooperative settings, adapting the model by freezing most of its parameters and adding a few lightweight modules. We demonstrate in our experiments that the proposed framework can effectively utilize cooperative observations and outperform other state-of-the-art approaches in both simulated and real-world cooperative perception benchmarks while requiring substantially fewer tunable parameters with reduced communication costs. Our source code is available at https://github.com/PurdueDigitalTwin/MACP.

Related papers

Err

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.