CoDS: Robust Collaborative Perception via Expert-driven Detection and BEV Segmentation

• URL: http://arxiv.org/abs/2608.14085v1
• Date: Fri, 14 Aug 2026 08:47:28 GMT
• Title: CoDS: Robust Collaborative Perception via Expert-driven Detection and BEV Segmentation
• Abstract summary: Collaborative perception breaks through single-view limitations via multi-agent information exchange.<n>However, multi-source noise such as pose errors and communication delays degrades fusion feature quality.<n>We propose a robust Collaborative perception framework with expert-driven Detection and bev (CoDS)
• Score: 13.629082376442405
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Collaborative perception breaks through single-view limitations via multi-agent information exchange. However, multi-source noise such as pose errors and communication delays degrades fusion feature quality, constraining perception performance. Joint training of detection and BEV segmentation provides a natural remedy, where segmented road regions help constrain target distributions and detection bounding boxes help recover ambiguous segmentation boundaries. To this end, we propose a robust Collaborative perception framework with expert-driven Detection and bev Segmentation (CoDS). To address spatial inconsistency in fusion quality, we first introduce the Collaborative Reliability Map (CoRM) to explicitly quantify feature quality distribution. Based on CoRM, we design the Semantic Mixture-of-Experts (S-MoE) module to extract differentiated features for inconsistent feature demands. Finally, to further mitigate feature noise degradation, the Bidirectional Task Complementary Interaction (BTCI) refines task-aware features through bidirectional injection. Extensive experiments on OPV2V and V2V4Real datasets show that our CoDS surpasses existing baselines on both tasks and maintains stable robustness under multi-source noise. Code: https://github.com/JinlongW128/CoDS and https://openi.pcl.ac.cn/OpenAIDriving/CoDS.

Related papers

• CauseCollab: Causal Unified and Modality-Agnostic Network for Heterogeneous Collaborative Perception [16.26142526400162]
  Collaborative perception enhances environment understanding through multi-agent information sharing.<n>Recent protocol-based two-stage methods alleviate this problem by mapping heterogeneous features into a shared protocol space.<n>We propose CauseCollab, a causal unified and modality-agnostic network.
  arXiv  Detail & Related papers  (2026-09-03T13:19:50Z)
• Complementarity-Supervised Spectral-Band Routing for Multimodal Emotion Recognition [60.20529806857076]
  Multimodal emotion recognition fuses cues such as text, video, and audio to understand individual emotional states.<n>Prior methods face two main limitations: mechanically relying on independent unimodal performance, and coarse-grained fusion conflicting with the fine-grained representations required by emotion tasks.<n>We propose the Complementarity-Supervised Multi-Band Expert Network, named Atsuko, to model fine-grained complementary features via multi-scale band decomposition and expert collaboration.
  arXiv  Detail & Related papers  (2026-03-07T03:58:48Z)
• SDCoNet: Saliency-Driven Multi-Task Collaborative Network for Remote Sensing Object Detection [7.016133328153285]
  In remote sensing images, complex backgrounds, weak object signals, and small object scales make accurate detection particularly challenging.<n>A common strategy is to integrate single-image super-resolution (SR) before detection.<n>We propose a Saliency-Driven multi-task Collaborative Network (SDCoNet) that couples SR and detection through implicit feature sharing.
  arXiv  Detail & Related papers  (2026-01-18T17:36:48Z)
• CoDS: Enhancing Collaborative Perception in Heterogeneous Scenarios via Domain Separation [25.442016145030383]
  Collaborative perception has been proven to improve individual perception in autonomous driving.<n>Most methods assume identical encoders for all agents, which does not hold true when these models are deployed in real-world applications.<n>Existing methods usually align neighbor features to those of the ego vehicle, which is vulnerable to noise from domain gaps.
  arXiv  Detail & Related papers  (2025-10-15T11:29:14Z)
• 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)
• Object Segmentation by Mining Cross-Modal Semantics [68.88086621181628]
  We propose a novel approach by mining the Cross-Modal Semantics to guide the fusion and decoding of multimodal features. Specifically, we propose a novel network, termed XMSNet, consisting of (1) all-round attentive fusion (AF), (2) coarse-to-fine decoder (CFD), and (3) cross-layer self-supervision.
  arXiv  Detail & Related papers  (2023-05-17T14:30:11Z)
• Discriminative Co-Saliency and Background Mining Transformer for Co-Salient Object Detection [111.04994415248736]
  We propose a Discriminative co-saliency and background Mining Transformer framework (DMT) We use two types of pre-defined tokens to mine co-saliency and background information via our proposed contrast-induced pixel-to-token correlation and co-saliency token-to-token correlation modules. Experimental results on three benchmark datasets demonstrate the effectiveness of our proposed method.
  arXiv  Detail & Related papers  (2023-04-30T15:56:47Z)
• Semi-supervised Domain Adaptive Structure Learning [72.01544419893628]
  Semi-supervised domain adaptation (SSDA) is a challenging problem requiring methods to overcome both 1) overfitting towards poorly annotated data and 2) distribution shift across domains. We introduce an adaptive structure learning method to regularize the cooperation of SSL and DA.
  arXiv  Detail & Related papers  (2021-12-12T06:11:16Z)
• Specificity-preserving RGB-D Saliency Detection [103.3722116992476]
  We propose a specificity-preserving network (SP-Net) for RGB-D saliency detection. Two modality-specific networks and a shared learning network are adopted to generate individual and shared saliency maps. Experiments on six benchmark datasets demonstrate that our SP-Net outperforms other state-of-the-art methods.
  arXiv  Detail & Related papers  (2021-08-18T14:14:22Z)
• Batch Coherence-Driven Network for Part-aware Person Re-Identification [79.33809815035127]
  Existing part-aware person re-identification methods typically employ two separate steps: namely, body part detection and part-level feature extraction. We propose NetworkBCDNet that bypasses body part during both the training and testing phases while still semantically aligned features.
  arXiv  Detail & Related papers  (2020-09-21T09:04:13Z)

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.