Salvato in:
Dettagli Bibliografici
Autori principali: Liu, Yuntao, Huang, Qian, Li, Rongpeng, Chen, Xianfu, Zhao, Zhifeng, Zhao, Shuyuan, Zhu, Yongdong, Zhang, Honggang
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:https://arxiv.org/abs/2307.16517
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916117363032064
author Liu, Yuntao
Huang, Qian
Li, Rongpeng
Chen, Xianfu
Zhao, Zhifeng
Zhao, Shuyuan
Zhu, Yongdong
Zhang, Honggang
author_facet Liu, Yuntao
Huang, Qian
Li, Rongpeng
Chen, Xianfu
Zhao, Zhifeng
Zhao, Shuyuan
Zhu, Yongdong
Zhang, Honggang
contents Collaborative perception by leveraging the shared semantic information plays a crucial role in overcoming the individual limitations of isolated agents. However, existing collaborative perception methods tend to focus solely on the spatial features of semantic information, while neglecting the importance of the temporal dimension. Consequently, the potential benefits of collaboration remain underutilized. In this article, we propose Select2Col, a novel collaborative perception framework that takes into account the \underline{s}patial-t\underline{e}mpora\underline{l} importanc\underline{e} of semanti\underline{c} informa\underline{t}ion. Within the Select2Col, we develop a collaborator selection method that utilizes a lightweight graph neural network (GNN) to estimate the importance of semantic information (IoSI) of each collaborator in enhancing perception performance, thereby identifying contributive collaborators while excluding those that potentially bring negative impact. Moreover, we present a semantic information fusion algorithm called HPHA (historical prior hybrid attention), which integrates multi-scale attention and short-term attention modules to capture the IoSI in feature representation from the spatial and temporal dimensions respectively, and assigns IoSI-consistent weights for efficient fusion of information from selected collaborators. Extensive experiments on three open datasets demonstrate that our proposed Select2Col significantly improves the perception performance compared to state-of-the-art approaches. The code associated with this research is publicly available at https://github.com/huangqzj/Select2Col/.
format Preprint
id arxiv_https___arxiv_org_abs_2307_16517
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Select2Col: Leveraging Spatial-Temporal Importance of Semantic Information for Efficient Collaborative Perception
Liu, Yuntao
Huang, Qian
Li, Rongpeng
Chen, Xianfu
Zhao, Zhifeng
Zhao, Shuyuan
Zhu, Yongdong
Zhang, Honggang
Computer Vision and Pattern Recognition
Artificial Intelligence
Collaborative perception by leveraging the shared semantic information plays a crucial role in overcoming the individual limitations of isolated agents. However, existing collaborative perception methods tend to focus solely on the spatial features of semantic information, while neglecting the importance of the temporal dimension. Consequently, the potential benefits of collaboration remain underutilized. In this article, we propose Select2Col, a novel collaborative perception framework that takes into account the \underline{s}patial-t\underline{e}mpora\underline{l} importanc\underline{e} of semanti\underline{c} informa\underline{t}ion. Within the Select2Col, we develop a collaborator selection method that utilizes a lightweight graph neural network (GNN) to estimate the importance of semantic information (IoSI) of each collaborator in enhancing perception performance, thereby identifying contributive collaborators while excluding those that potentially bring negative impact. Moreover, we present a semantic information fusion algorithm called HPHA (historical prior hybrid attention), which integrates multi-scale attention and short-term attention modules to capture the IoSI in feature representation from the spatial and temporal dimensions respectively, and assigns IoSI-consistent weights for efficient fusion of information from selected collaborators. Extensive experiments on three open datasets demonstrate that our proposed Select2Col significantly improves the perception performance compared to state-of-the-art approaches. The code associated with this research is publicly available at https://github.com/huangqzj/Select2Col/.
title Select2Col: Leveraging Spatial-Temporal Importance of Semantic Information for Efficient Collaborative Perception
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2307.16517