CoDS: Robust Collaborative Perception via Expert-driven Detection and BEV Segmentation

2026-08-14

AI Summary

This study addresses feature degradation in collaborative perception caused by multi-source noise by proposing the CoDS framework. The method quantifies feature quality via a collaborative reliability graph and incorporates semantic mixture-of-experts with a bidirectional task-complementary interaction mechanism. By jointly training detection and BEV segmentation tasks, CoDS leverages their complementary strengths to effectively suppress noise interference. Experiments on the OPV2V and V2V4Real datasets demonstrate that CoDS significantly outperforms existing baselines and exhibits superior robustness under complex multi-source noise conditions. These findings establish CoDS as a promising paradigm for enhancing the reliability of collaborative perception systems in challenging environments.

Abstract

Collaborative perception breaks through single-view limitations via multi-agent information exchange. However, multi-source noise such as pose errors and communication delays degrades fusion feature quality, constraining perception performance. Joint training of detection and BEV segmentation provides a natural remedy, where segmented road regions help constrain target distributions and detection bounding boxes help recover ambiguous segmentation boundaries. To this end, we propose a robust Collaborative perception framework with expert-driven Detection and bev Segmentation (CoDS). To address spatial inconsistency in fusion quality, we first introduce the Collaborative Reliability Map (CoRM) to explicitly quantify feature quality distribution. Based on CoRM, we design the Semantic Mixture-of-Experts (S-MoE) module to extract differentiated features for inconsistent feature demands. Finally, to further mitigate feature noise degradation, the Bidirectional Task Complementary Interaction (BTCI) refines task-aware features through bidirectional injection. Extensive experiments on OPV2V and V2V4Real datasets show that our CoDS surpasses existing baselines on both tasks and maintains stable robustness under multi-source noise. Code: https://github.com/JinlongW128/CoDS and https://openi.pcl.ac.cn/OpenAIDriving/CoDS.

Problem

• Collaborative Perception
• Multi-source Noise
• Feature Fusion
• Robustness

Innovation

• Collaborative Reliability Map
• Semantic Mixture-of-Experts
• Bidirectional Task Complementary Interaction
• BEV Segmentation
• Robust Collaborative Perception