analiza aiqbench
GT-Space introduces a scalable framework for heterogeneous collaborative perception in autonomous driving by using ground-truth labels to create a unified feature space. This approach eliminates the need for complex pairwise alignment or retraining encoders, allowing diverse agents with different sensing modalities to fuse data efficiently via simple adapter modules. The method demonstrates improved detection accuracy across simulation and real-world datasets, addressing a critical bottleneck in multi-agent sensor fusion.
GT-Space: Enhancing Heterogeneous Collaborative Perception with Ground Truth Feature Space
arXiv:2603.19308v2 Announce Type: replace-cross Abstract: In autonomous driving, multi-agent collaborative perception enhances sensing capabilities by enabling agents to share perceptual data. A key challenge lies in handling {\em heterogeneous} features from agents equipped with different sensing modalities or model architectures, which complicates data fusion. Existing approaches often require retraining encoders or designing interpreter modules for pairwise feature alignment, but these solutions are not scalable in practice. To address this, we propose {\em GT-Space}, a flexible and scalable collaborative perception framework for heterogeneous agents. GT-Space constructs a common feature space from ground-truth labels, providing a unified reference for feature alignment. With this shared space, agents only need a single adapter module to project their features, eliminating the need for pairwise interactions with other agents. Furthermore, we design a fusion network trained with contrastive losses across diverse modality combinations. Extensive experiments on simulation datasets (OPV2V and V2XSet) and a real-world dataset (RCooper) demonstrate that GT-Space consistently outperforms baselines in detection accuracy while delivering robust performance. Our code will be released at https://github.com/KingScar/GT-Space.
Abstract:In autonomous driving, multi-agent collaborative perception enhances sensing capabilities by enabling agents to share perceptual data. A key challenge lies in handling {\em heterogeneous} features from agents equipped with different sensing modalities or model architectures, which complicates data fusion. Existing approaches often require retraining encoders or designing interpreter modules for pairwise feature alignment, but these solutions are not scalable in practice. To address this, we propose {\em GT-Space}, a flexible and scalable collaborative perception framework for heterogeneous agents. GT-Space constructs a common feature space from ground-truth labels, providing a unified reference for feature alignment. With this shared space, agents only need a single adapter module to project their features, eliminating the need for pairwise interactions with other agents. Furthermore, we design a fusion network trained with contrastive losses across diverse modality combinations. Extensive experiments on simulation datasets (OPV2V and V2XSet) and a real-world dataset (RCooper) demonstrate that GT-Space consistently outperforms baselines in detection accuracy while delivering robust performance. Our code will be released at this https URL.
Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Multiagent Systems (cs.MA)
arXiv:2603.19308 [cs.LG]
(or arXiv:2603.19308v2 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2603.19308 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 265 cuvinte
Subiecte conexe
News
Quantum Computing Report · 25 iul. 2026
AGT-CV: An Aerial-Ground Team Cross-View Dataset for Heterogeneous Robot Teams in Unstructured Environments
arXiv · 5 oct. 2026
Imaginative Perception Tokens Enhance Spatial Reasoning in Multimodal Language Models
arXiv · 18 aug. 2026
CauseCollab: Causal Unified and Modality-Agnostic Network for Heterogeneous Collaborative Perception
arXiv · 5 sept. 2026