Bridging the Domain Gap for Multi-Agent Perception

2022-10-16 · Runsheng Xu, Jinlong Li, Xiaoyu Dong, Hongkai Yu, Jiaqi Ma

Existing multi-agent perception algorithms usually select to share deep neural features extracted from raw sensing data between agents, achieving a trade-off between accuracy and communication bandwidth limit. However, these methods assume all agents have identical neural networks, which might not be practical in the real world. The transmitted features can have a large domain gap when the models differ, leading to a dramatic performance drop in multi-agent perception. In this paper, we propose the first lightweight framework to bridge such domain gaps for multi-agent perception, which can be a plug-in module for most existing systems while maintaining confidentiality. Our framework consists of a learnable feature resizer to align features in multiple dimensions and a sparse cross-domain transformer for domain adaption. Extensive experiments on the public multi-agent perception dataset V2XSet have demonstrated that our method can effectively bridge the gap for features from different domains and outperform other baseline methods significantly by at least 8% for point-cloud-based 3D object detection.

📄 PDF Abstract BibTeX arXiv:2210.08451

Code (1)

derrickxunu/mpda 공식 구현 pytorch

Tasks

3D Object Detection Domain Adaptation object-detection Object Detection

Methods 이 논문이 사용한 방법론

ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…

S2R-ViT for Multi-Agent Cooperative Perception: Bridging the Gap from Simulation to Reality

2023-07-16 · Jinlong Li, Runsheng Xu, Xinyu Liu, Baolu Li 외

Due to the lack of enough real multi-agent data and time-consuming of labeling, existing multi-agent cooperative perception algorithms usually select the simulated sensor data for training and validating. However, the pe…

3D Object Detection object-detection Object Detection Transfer Learning

Bridging the Semantic Chasm: Synergistic Conceptual Anchoring for Generalized Few-Shot and Zero-Shot OOD Perception

2026-01-30 · Alexandros Christoforos, Sarah Jenkins, Michael Brown, Tuan Pham 외 arxiv

This manuscript presents a pioneering Synergistic Neural Agents Network (SynerNet) framework designed to mitigate the phenomenon of cross-modal alignment degeneration in Vision-Language Models (VLMs) when encountering Ou…

Bridging the Perception Gap: A Lightweight Coarse-to-Fine Architecture for Edge Audio Systems

2026-01-22 · Hengfan Zhang, Yueqian Lin, Hai Helen Li, Yiran Chen arxiv

Deploying Audio-Language Models (Audio-LLMs) on edge infrastructure exposes a persistent tension between perception depth and computational efficiency. Lightweight local models tend to produce passive perception - generi…

Computational Efficiency

Move What Matters: Parameter-Efficient Domain Adaptation via Optimal Transport Flow for Collaborative Perception

2026-02-12 · Zesheng Jia, Jin Wang, Siao Liu, Lingzhi Li 외 arxiv

Fast domain adaptation remains a fundamental challenge for deploying multi-agent systems across diverse environments in Vehicle-to-Everything (V2X) collaborative perception. Despite the success of Parameter-Efficient Fin…

parameter-efficient fine-tuning Domain Adaptation

Breaking Data Silos: Cross-Domain Learning for Multi-Agent Perception from Independent Private Sources

2024-02-06 · Jinlong Li, Baolu Li, Xinyu Liu, Runsheng Xu 외

The diverse agents in multi-agent perception systems may be from different companies. Each company might use the identical classic neural network architecture based encoder for feature extraction. However, the data sourc…

3D Object Detection object-detection Object Detection