HeatV2X: Scalable Heterogeneous Collaborative Perception via Efficient Alignment and Interaction

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhao, Yueran, Zhang, Zhang, Sun, Chao, Wang, Tianze, Yue, Chao, Li, Nuoran
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912706637856768
author Zhao, Yueran
Zhang, Zhang
Sun, Chao
Wang, Tianze
Yue, Chao
Li, Nuoran
author_facet Zhao, Yueran
Zhang, Zhang
Sun, Chao
Wang, Tianze
Yue, Chao
Li, Nuoran
contents Vehicle-to-Everything (V2X) collaborative perception extends sensing beyond single vehicle limits through transmission. However, as more agents participate, existing frameworks face two key challenges: (1) the participating agents are inherently multi-modal and heterogeneous, and (2) the collaborative framework must be scalable to accommodate new agents. The former requires effective cross-agent feature alignment to mitigate heterogeneity loss, while the latter renders full-parameter training impractical, highlighting the importance of scalable adaptation. To address these issues, we propose Heterogeneous Adaptation (HeatV2X), a scalable collaborative framework. We first train a high-performance agent based on heterogeneous graph attention as the foundation for collaborative learning. Then, we design Local Heterogeneous Fine-Tuning and Global Collaborative Fine-Tuning to achieve effective alignment and interaction among heterogeneous agents. The former efficiently extracts modality-specific differences using Hetero-Aware Adapters, while the latter employs the Multi-Cognitive Adapter to enhance cross-agent collaboration and fully exploit the fusion potential. These designs enable substantial performance improvement of the collaborative framework with minimal training cost. We evaluate our approach on the OPV2V-H and DAIR-V2X datasets. Experimental results demonstrate that our method achieves superior perception performance with significantly reduced training overhead, outperforming existing state-of-the-art approaches. Our implementation will be released soon.
format Preprint
id arxiv_https___arxiv_org_abs_2511_10211
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle HeatV2X: Scalable Heterogeneous Collaborative Perception via Efficient Alignment and Interaction
Zhao, Yueran
Zhang, Zhang
Sun, Chao
Wang, Tianze
Yue, Chao
Li, Nuoran
Computer Vision and Pattern Recognition
Vehicle-to-Everything (V2X) collaborative perception extends sensing beyond single vehicle limits through transmission. However, as more agents participate, existing frameworks face two key challenges: (1) the participating agents are inherently multi-modal and heterogeneous, and (2) the collaborative framework must be scalable to accommodate new agents. The former requires effective cross-agent feature alignment to mitigate heterogeneity loss, while the latter renders full-parameter training impractical, highlighting the importance of scalable adaptation. To address these issues, we propose Heterogeneous Adaptation (HeatV2X), a scalable collaborative framework. We first train a high-performance agent based on heterogeneous graph attention as the foundation for collaborative learning. Then, we design Local Heterogeneous Fine-Tuning and Global Collaborative Fine-Tuning to achieve effective alignment and interaction among heterogeneous agents. The former efficiently extracts modality-specific differences using Hetero-Aware Adapters, while the latter employs the Multi-Cognitive Adapter to enhance cross-agent collaboration and fully exploit the fusion potential. These designs enable substantial performance improvement of the collaborative framework with minimal training cost. We evaluate our approach on the OPV2V-H and DAIR-V2X datasets. Experimental results demonstrate that our method achieves superior perception performance with significantly reduced training overhead, outperforming existing state-of-the-art approaches. Our implementation will be released soon.
title HeatV2X: Scalable Heterogeneous Collaborative Perception via Efficient Alignment and Interaction
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2511.10211