Metraipolis › archive › dc_c588055175df

CauseCollab: Causal Unified and Modality-Agnostic Network for Heterogeneous Collaborative Perception — arXiv:2609.03818

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.03818
License (as archived)
CC0-1.0
Archived
2026-10-17T01:11:23.156Z
SHA-256 of the archived text
27190dcee600852fca4cb911075f288773c409444a109701eecc9a7a2dd71a1d
Stable URL of this page
https://metraipolis.com/documento/dc_c588055175df

How to cite

CauseCollab: Causal Unified and Modality-Agnostic Network for Heterogeneous Collaborative Perception — arXiv:2609.03818 — arXiv (en), https://arxiv.org/abs/2609.03818 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c588055175df (Metraipolis archive dc_c588055175df, sha256 27190dcee600852fca4cb911075f288773c409444a109701eecc9a7a2dd71a1d)
BibTeX
@misc{dcc588055175df,
  title = {CauseCollab: Causal Unified and Modality-Agnostic Network for Heterogeneous Collaborative Perception — arXiv:2609.03818},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.03818},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c588055175df; sha256 27190dcee600852fca4cb911075f288773c409444a109701eecc9a7a2dd71a1d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.03818. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Collaborative perception enhances environment understanding through multi-agent information sharing, but its performance in real-world scenarios is constrained by heterogeneous sensor modalities and model architectures. Recent protocol-based two-stage methods alleviate this problem by mapping heterogeneous features into a shared protocol space; however, independently trained modality-specific converters often generate modality-specific pseudo-protocol distributions, leading to semantic inconsistency and error accumulation, which is particularly pronounced in scenarios with large modality discrepancies. To address this issue, we propose CauseCollab, a causal unified and modality-agnostic network. CauseCollab formulates representation learning in the protocol space from a causal perspective, explicitly disentangling semantic factors from modality-specific statistical confounders via causal metric learning. Meanwhile, CauseCollab adopts context-guided Unified Converter for heterogeneous modalities to ensure cross-modal semantic consistency. In addition, integrating new modalities only requires training adapters with minimal parameters. Extensive experiments on the OPV2V and DAIR-V2X datasets demonstrate that CauseCollab achieves state-of-the-art performance, with more significant gains in scenarios involving large modality gaps.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-04 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.03818 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-17T00:28:02.880Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-04?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).