EUVIMEDEUVIMED entdecken
Crossref

From Discriminative to Generative: A Diffusion-Based Paradigm for Multi-Agent Collaborative Perception

Kexin Gong, Puyi Yao, Guiyang Luo, Quan Yuan, Tiange Fu, Hui Zhang, Jinglin Li

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (6) · 4266-4274

DOI: 10.1609/aaai.v40i6.42423 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Kexin Gong und 6 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Collaborative perception leveraging intermediate feature fusion has emerged as a leading paradigm to significantly enhance the environmental perception capabilities of autonomous driving systems. However, existing methods typically rely on discriminative supervision guided by downstream tasks. This paradigm compels models to learn minimal, task-specific representations, which conflicts with the goal of cooperative perception to capture comprehensive information, thereby limiting generalization. To address this issue, we propose DiGS-CP, a novel two-stage generative supervised collaborative perception framework. Specifically, we introduce a diffusion-based generative task that conditions on fused object-level features to generate representations of object-level point clouds. The proposed generative supervision provides fine-grained, task-agnostic signals that encourages the fusion module to learn comprehensive representations beyond task-specific requirements. By preserving and integrating complementary information from collaborative agents, our approach overcomes the limitations of task-specific learning and enhances the generalizability of the learned features. Furthermore, our two-stage architecture requires agents to transmit only object-level features, significantly reducing communication overhead. Extensive experiments on three benchmark datasets demonstrate that DiGS-CP achieves state-of-the-art performance in 3D object detection, while maintaining low bandwidth requirements and exhibiting excellent generalization ability.

Zitieren

APA

Gong, K., Yao, P., Luo, G., Yuan, Q., Fu, T., Zhang, H., & Li, J. (2026). From Discriminative to Generative: A Diffusion-Based Paradigm for Multi-Agent Collaborative Perception. Proceedings of the AAAI Conference on Artificial Intelligence, 40(6), 4266-4274. https://doi.org/10.1609/aaai.v40i6.42423

Vancouver

Gong K, Yao P, Luo G, Yuan Q, Fu T, Zhang H, et al. From Discriminative to Generative: A Diffusion-Based Paradigm for Multi-Agent Collaborative Perception. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(6):4266-4274. doi:10.1609/aaai.v40i6.42423

BibTeX
@article{Gong2026,
  author = {Gong, Kexin and Yao, Puyi and Luo, Guiyang and Yuan, Quan and Fu, Tiange and Zhang, Hui and Li, Jinglin},
  title = {From Discriminative to Generative: A Diffusion-Based Paradigm for Multi-Agent Collaborative Perception},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {6},
  pages = {4266--4274},
  doi = {10.1609/aaai.v40i6.42423}
}
Kostenlos starten →