REVIEW 6 cited by
An Extensible Framework for Open Heterogeneous Collaborative Perception
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
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
Forward citations
Cited by 6 Pith papers
-
AirV2X: Unified Air-Ground Vehicle-to-Everything Collaboration
AirV2X-Perception is a 6.73-hour simulated dataset and benchmark for collaborative perception with up to 5 vehicles, 5 roadside units, and 5 drones.
-
HeteroPROPMT: A Real-time and Privacy-Preserving Heterogeneous Collaborative Perception Framework
A prompt-based, privacy-preserving heterogeneity-alignment framework that uses low-rank FiLM to adapt BEV features and an autoencoder-based classifier for metadata-free modality routing.
-
Progressive Bird's Eye View Perception for Safety-Critical Autonomous Driving: A Comprehensive Survey
A safety-critical survey that organizes BEV perception into single-modality, multimodal, and collaborative stages and consolidates robustness evidence that multimodal fusion degrades far less than single-modality perc...
-
Learning-Based Hybrid Neural Receiver for 6G-V2X Communications
A transformer plus graph-neural-network receiver replaces the whole physical-layer receiver chain in simulated 6G V2X links and beats prior neural receivers by about 0.5 dB.
-
Differential Transformer-driven 6G Physical Layer for Collaborative Perception Enhancement
A Differential Transformer-based neural receiver outperforms a CNN-based receiver on simulated 6G V2X links and improves collaborative perception accuracy among four connected vehicles.
-
Automated Vehicles Should be Connected with Natural Language
A vision paper recommending natural language as the universal communication medium for connected and automated vehicles.
Discussion (0). Sign in to comment.