CoBEVMoE: Heterogeneity-aware Feature Fusion with Dynamic Mixture-of-Experts for Collaborative Perception

• URL: http://arxiv.org/abs/2509.17107v1
• Date: Sun, 21 Sep 2025 14:56:05 GMT
• Title: CoBEVMoE: Heterogeneity-aware Feature Fusion with Dynamic Mixture-of-Experts for Collaborative Perception
• Authors: Lingzhao Kong, Jiacheng Lin, Siyu Li, Kai Luo, Zhiyong Li, Kailun Yang,
• Abstract summary: We propose a novel collaborative perception framework that operates in the Bird's Eye View (BEV) space.<n>We introduce a Dynamic Expert Metric Loss (DEML) to enhance inter-expert diversity and improve the discriminability of the fused representation.
• Score: 21.27356211403264
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Collaborative perception aims to extend sensing coverage and improve perception accuracy by sharing information among multiple agents. However, due to differences in viewpoints and spatial positions, agents often acquire heterogeneous observations. Existing intermediate fusion methods primarily focus on aligning similar features, often overlooking the perceptual diversity among agents. To address this limitation, we propose CoBEVMoE, a novel collaborative perception framework that operates in the Bird's Eye View (BEV) space and incorporates a Dynamic Mixture-of-Experts (DMoE) architecture. In DMoE, each expert is dynamically generated based on the input features of a specific agent, enabling it to extract distinctive and reliable cues while attending to shared semantics. This design allows the fusion process to explicitly model both feature similarity and heterogeneity across agents. Furthermore, we introduce a Dynamic Expert Metric Loss (DEML) to enhance inter-expert diversity and improve the discriminability of the fused representation. Extensive experiments on the OPV2V and DAIR-V2X-C datasets demonstrate that CoBEVMoE achieves state-of-the-art performance. Specifically, it improves the IoU for Camera-based BEV segmentation by +1.5% on OPV2V and the AP@50 for LiDAR-based 3D object detection by +3.0% on DAIR-V2X-C, verifying the effectiveness of expert-based heterogeneous feature modeling in multi-agent collaborative perception. The source code will be made publicly available at https://github.com/godk0509/CoBEVMoE.

Related papers

• Modeling Cross-vision Synergy for Unified Large Vision Model [130.37489011094036]
  PolyV is a unified large vision model that achieves cross-vision synergy at both the architectural and training levels.<n>PolyV consistently outperforms existing models, achieving over 10% average improvement over its backbone.
  arXiv  Detail & Related papers  (2026-03-03T22:44:43Z)
• Code-in-the-Loop Forensics: Agentic Tool Use for Image Forgery Detection [59.04089915447622]
  ForenAgent is an interactive IFD framework that enables MLLMs to autonomously generate, execute, and refine Python-based low-level tools around the detection objective.<n>Inspired by human reasoning, we design a dynamic reasoning loop comprising global perception, local focusing, iterative probing, and holistic adjudication.<n>Experiments show that ForenAgent exhibits emergent tool-use competence and reflective reasoning on challenging IFD tasks.
  arXiv  Detail & Related papers  (2025-12-18T08:38:44Z)
• INSTINCT: Instance-Level Interaction Architecture for Query-Based Collaborative Perception [6.018757656052237]
  Collaborative perception systems overcome single-vehicle limitations by integrating multi-agent sensory data, improving accuracy and safety.<n>Previous works proves that query-based instance-level interaction reduces bandwidth demands and manual priors, however, LiDAR-focused implementations in collaborative perception remain underdeveloped.<n>We propose INSTINCT, a novel collaborative perception framework featuring three core components: 1) a quality-aware filtering mechanism for high-quality instance feature selection; 2) a dual-branch detection routing scheme to decouple collaboration-irrelevant and collaboration-relevant instances; and 3) a Cross Agent Local Instance Fusion module to aggregate local hybrid instance features.
  arXiv  Detail & Related papers  (2025-09-28T07:16:32Z)
• V2X-DGPE: Addressing Domain Gaps and Pose Errors for Robust Collaborative 3D Object Detection [18.694510415777632]
  V2X-DGPE is a high-accuracy and robust V2X feature-level collaborative perception framework.<n>The proposed method outperforms existing approaches, achieving state-of-the-art detection performance.
  arXiv  Detail & Related papers  (2025-01-04T19:28:55Z)
• CooPre: Cooperative Pretraining for V2X Cooperative Perception [47.00472259100765]
  CooPre is a self-supervised learning framwork for V2X cooperative perception.<n>We develop a V2X bird-eye-view (BEV) guided masking strategy which effectively allows the model to pay attention to 3D features across heterogeneous V2X agents.<n>CooPre achieves a 4% mAP improvement on V2X-Real dataset and surpasses baseline performance using only 50% of the training data.
  arXiv  Detail & Related papers  (2024-08-20T23:39:26Z)
• IFTR: An Instance-Level Fusion Transformer for Visual Collaborative Perception [9.117534139771738]
  Multi-agent collaborative perception has emerged as a widely recognized technology in the field of autonomous driving. Current collaborative perception predominantly relies on LiDAR point clouds, with significantly less attention given to methods using camera images. This work proposes an instance-level fusion transformer for visual collaborative perception.
  arXiv  Detail & Related papers  (2024-07-13T11:38:15Z)
• UVCPNet: A UAV-Vehicle Collaborative Perception Network for 3D Object Detection [11.60579201022641]
  We propose a framework specifically designed for aerial-ground collaboration. We develop a virtual dataset named V2U-COO for our research. Second, we design a Cross-Domain Cross-Adaptation (CDCA) module to align the target information. Third, we introduce a Collaborative Depth Optimization (CDO) module to obtain more precise depth estimation results.
  arXiv  Detail & Related papers  (2024-06-07T05:25:45Z)
• What Makes Good Collaborative Views? Contrastive Mutual Information Maximization for Multi-Agent Perception [52.41695608928129]
  Multi-agent perception (MAP) allows autonomous systems to understand complex environments by interpreting data from multiple sources. This paper investigates intermediate collaboration for MAP with a specific focus on exploring "good" properties of collaborative view. We propose a novel framework named CMiMC for intermediate collaboration.
  arXiv  Detail & Related papers  (2024-03-15T07:18:55Z)
• An Extensible Framework for Open Heterogeneous Collaborative Perception [58.70875361688463]
  Collaborative perception aims to mitigate the limitations of single-agent perception. In this paper, we introduce a new open heterogeneous problem: how to accommodate continually emerging new heterogeneous agent types into collaborative perception. We propose HEterogeneous ALliance (HEAL), a novel collaborative perception framework.
  arXiv  Detail & Related papers  (2024-01-25T05:55:03Z)
• Learning with MISELBO: The Mixture Cookbook [62.75516608080322]
  We present the first ever mixture of variational approximations for a normalizing flow-based hierarchical variational autoencoder (VAE) with VampPrior and a PixelCNN decoder network. We explain this cooperative behavior by drawing a novel connection between VI and adaptive importance sampling. We obtain state-of-the-art results among VAE architectures in terms of negative log-likelihood on the MNIST and FashionMNIST datasets.
  arXiv  Detail & Related papers  (2022-09-30T15:01:35Z)
• A Joint Cross-Attention Model for Audio-Visual Fusion in Dimensional Emotion Recognition [46.443866373546726]
  We focus on dimensional emotion recognition based on the fusion of facial and vocal modalities extracted from videos. We propose a joint cross-attention model that relies on the complementary relationships to extract the salient features. Our proposed A-V fusion model provides a cost-effective solution that can outperform state-of-the-art approaches.
  arXiv  Detail & Related papers  (2022-03-28T14:09:43Z)
• DecAug: Augmenting HOI Detection via Decomposition [54.65572599920679]
  Current algorithms suffer from insufficient training samples and category imbalance within datasets. We propose an efficient and effective data augmentation method called DecAug for HOI detection. Experiments show that our method brings up to 3.3 mAP and 1.6 mAP improvements on V-COCO and HICODET dataset.
  arXiv  Detail & Related papers  (2020-10-02T13:59:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.