提出HyDRA框架，实现异构协同感知的无代价扩展。
HyDRA: Hybrid Domain-Aware Robust Architecture for Heterogeneous Collaborative Perception
- 融合中间与晚期融合，动态识别异构节点分配至晚融合分支。
- 无需额外训练，性能媲美当前最优方法，支持零成本扩容。
- 用中间融合检测作为锚点优化定位，缓解晚融合误差问题。
在协同感知中，由于模型架构或训练数据分布差异导致的异构性会降低代理性能。为此，我们提出HyDRA（混合域感知鲁棒架构），一种集成中间融合与晚融合的统一管道，构建于域感知框架内。引入轻量级域分类器，动态识别异构代理并将其分配至晚融合分支。同时，提出基于锚点的姿态图优化方法，利用中间融合中的可靠检测作为固定空间锚点，缓解晚融合固有的定位误差。大量实验表明，尽管无需额外训练，HyDRA性能可媲美当前最优的异构感知方法。更重要的是，随着协作代理数量增加，性能仍能保持稳定，实现无需重训的零成本扩展。
原文摘要 · Abstract (English)
In collaborative perception, an agent's performance can be degraded by heterogeneity arising from differences in model architecture or training data distributions. To address this challenge, we propose HyDRA (Hybrid Domain-Aware Robust Architecture), a unified pipeline that integrates intermediate and late fusion within a domain-aware framework. We introduce a lightweight domain classifier that dynamically identifies heterogeneous agents and assigns them to the late-fusion branch. Furthermore, we propose anchor-guided pose graph optimization to mitigate localization errors inherent in late fusion, leveraging reliable detections from intermediate fusion as fixed spatial anchors. Extensive experiments demonstrate that, despite requiring no additional training, HyDRA achieves performance comparable to state-of-the-art heterogeneity-aware CP methods. Importantly, this performance is maintained as the number of collaborating agents increases, enabling zero-cost scaling without retraining.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。