An Extensible Framework for Open Heterogeneous Collaborative Perception

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lu, Yifan, Hu, Yue, Zhong, Yiqi, Wang, Dequan, Wang, Yanfeng, Chen, Siheng
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914735457304576
author Lu, Yifan
Hu, Yue
Zhong, Yiqi
Wang, Dequan
Wang, Yanfeng
Chen, Siheng
author_facet Lu, Yifan
Hu, Yue
Zhong, Yiqi
Wang, Dequan
Wang, Yanfeng
Chen, Siheng
contents Collaborative perception aims to mitigate the limitations of single-agent perception, such as occlusions, by facilitating data exchange among multiple agents. However, most current works consider a homogeneous scenario where all agents use identity sensors and perception models. In reality, heterogeneous agent types may continually emerge and inevitably face a domain gap when collaborating with existing agents. In this paper, we introduce a new open heterogeneous problem: how to accommodate continually emerging new heterogeneous agent types into collaborative perception, while ensuring high perception performance and low integration cost? To address this problem, we propose HEterogeneous ALliance (HEAL), a novel extensible collaborative perception framework. HEAL first establishes a unified feature space with initial agents via a novel multi-scale foreground-aware Pyramid Fusion network. When heterogeneous new agents emerge with previously unseen modalities or models, we align them to the established unified space with an innovative backward alignment. This step only involves individual training on the new agent type, thus presenting extremely low training costs and high extensibility. To enrich agents' data heterogeneity, we bring OPV2V-H, a new large-scale dataset with more diverse sensor types. Extensive experiments on OPV2V-H and DAIR-V2X datasets show that HEAL surpasses SOTA methods in performance while reducing the training parameters by 91.5% when integrating 3 new agent types. We further implement a comprehensive codebase at: https://github.com/yifanlu0227/HEAL
format Preprint
id arxiv_https___arxiv_org_abs_2401_13964
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle An Extensible Framework for Open Heterogeneous Collaborative Perception
Lu, Yifan
Hu, Yue
Zhong, Yiqi
Wang, Dequan
Wang, Yanfeng
Chen, Siheng
Computer Vision and Pattern Recognition
Collaborative perception aims to mitigate the limitations of single-agent perception, such as occlusions, by facilitating data exchange among multiple agents. However, most current works consider a homogeneous scenario where all agents use identity sensors and perception models. In reality, heterogeneous agent types may continually emerge and inevitably face a domain gap when collaborating with existing agents. In this paper, we introduce a new open heterogeneous problem: how to accommodate continually emerging new heterogeneous agent types into collaborative perception, while ensuring high perception performance and low integration cost? To address this problem, we propose HEterogeneous ALliance (HEAL), a novel extensible collaborative perception framework. HEAL first establishes a unified feature space with initial agents via a novel multi-scale foreground-aware Pyramid Fusion network. When heterogeneous new agents emerge with previously unseen modalities or models, we align them to the established unified space with an innovative backward alignment. This step only involves individual training on the new agent type, thus presenting extremely low training costs and high extensibility. To enrich agents' data heterogeneity, we bring OPV2V-H, a new large-scale dataset with more diverse sensor types. Extensive experiments on OPV2V-H and DAIR-V2X datasets show that HEAL surpasses SOTA methods in performance while reducing the training parameters by 91.5% when integrating 3 new agent types. We further implement a comprehensive codebase at: https://github.com/yifanlu0227/HEAL
title An Extensible Framework for Open Heterogeneous Collaborative Perception
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2401.13964