# PEARL: A Lightweight Prompt-based Feature Interpreter Framework for Real-Time, Anonymous, and Heterogeneous Collaborative Perception

arXiv: https://arxiv.org/abs/2609.27123 · HTML: https://mlsanity.com/paper/2609.27123/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 30 of its 42 references that are in the map.
- First posted on arXiv 22 Sep 2026.

## Builds on (most cited first, 30 of 30)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [PointPillars: Fast Encoders for Object Detection from Point Clouds](https://mlsanity.com/paper/1812.05784/) (2018)
- [VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection](https://mlsanity.com/paper/1711.06396/) (2017)
- [V2X-ViT: Vehicle-to-Everything Cooperative Perception with Vision Transformer](https://mlsanity.com/paper/2203.10638/) (2022)
- [OPV2V: An Open Benchmark Dataset and Fusion Pipeline for Perception with Vehicle-to-Vehicle Communication](https://mlsanity.com/paper/2109.07644/) (2021)
- [DAIR-V2X: A Large-Scale Dataset for Vehicle-Infrastructure Cooperative 3D Object Detection](https://mlsanity.com/paper/2204.05575/) (2022)
- [Where2comm: Communication-Efficient Collaborative Perception via Spatial Confidence Maps](https://mlsanity.com/paper/2209.12836/) (2022)
- [CoBEVT: Cooperative Bird's Eye View Semantic Segmentation with Sparse Transformers](https://mlsanity.com/paper/2207.02202/) (2022)
- [Decorate the Newcomers: Visual Domain Prompt for Continual Test Time Adaptation](https://mlsanity.com/paper/2212.04145/) (2022)
- [An Extensible Framework for Open Heterogeneous Collaborative Perception](https://mlsanity.com/paper/2401.13964/) (2024)
- [HM-ViT: Hetero-modal Vehicle-to-Vehicle Cooperative perception with vision transformer](https://mlsanity.com/paper/2304.10628/) (2023)
- [Communication-Efficient Collaborative Perception via Information Filling with Codebook](https://mlsanity.com/paper/2405.04966/) (2024)
- [AD-CLIP: Adapting Domains in Prompt Space Using CLIP](https://mlsanity.com/paper/2308.05659/) (2023)
- [Bridging the Domain Gap for Multi-Agent Perception](https://mlsanity.com/paper/2210.08451/) (2022)
- [DI-V2X: Learning Domain-Invariant Representation for Vehicle-Infrastructure Collaborative 3D Object Detection](https://mlsanity.com/paper/2312.15742/) (2023)
- [Exploring Sparse Visual Prompt for Domain Adaptive Dense Prediction](https://mlsanity.com/paper/2303.09792/) (2023)
- [Domain-Controlled Prompt Learning](https://mlsanity.com/paper/2310.07730/) (2023)
- [Learning Domain-Aware Detection Head with Prompt Tuning](https://mlsanity.com/paper/2306.05718/) (2023)
- [One is Plenty: A Polymorphic Feature Interpreter for Immutable Heterogeneous Collaborative Perception](https://mlsanity.com/paper/2411.16799/) (2024)
- [A Spatial Calibration Method for Robust Cooperative Perception](https://mlsanity.com/paper/2304.12033/) (2023)
- [A Survey on Intermediate Fusion Methods for Collaborative Perception Categorized by Real World Challenges](https://mlsanity.com/paper/2404.16139/) (2024)
- [Robust Collaborative Perception without External Localization and Clock Devices](https://mlsanity.com/paper/2405.02965/) (2024)
- [DA-Ada: Learning Domain-Aware Adapter for Domain Adaptive Object Detection](https://mlsanity.com/paper/2410.09004/) (2024)
- [NegoCollab: A Common Representation Negotiation Approach for Heterogeneous Collaborative Perception](https://mlsanity.com/paper/2510.27647/) (2025)
- [UPRE: Zero-Shot Domain Adaptation for Object Detection via Unified Prompt and Representation Enhancement](https://mlsanity.com/paper/2507.00721/) (2025)
- [CoBEVMoE: Heterogeneity-aware Feature Fusion with Dynamic Mixture-of-Experts for Collaborative Perception](https://mlsanity.com/paper/2509.17107/) (2025)
- [Self-Localized Collaborative Perception](https://mlsanity.com/paper/2406.12712/) (2024)
- [Faster-HEAL: An Efficient and Privacy-Preserving Collaborative Perception Framework for Heterogeneous Autonomous Vehicles](https://mlsanity.com/paper/2603.07314/) (2026)
- [Prmpt2Adpt: Prompt-Based Zero-Shot Domain Adaptation for Resource-Constrained Environments](https://mlsanity.com/paper/2506.16994/) (2025)

## Abstract (arXiv)

Heterogeneity across Collaborative Perception (CP) agents is a major challenge for emerging CP frameworks due to domain gaps from differing sensors, architectures, and training data. Prior works mitigate this challenge by aligning features in a unified space via model retraining or per-agent-type interpreters. These strategies (a) require access to neighbor configurations, (b) do not fully address real-time CP deployment, and (c) generalize poorly to unseen agents joining at run time. To overcome these challenges, we present PEARL, a Prompt-Embedding framework for Anonymous and Real-time Lightweight heterogeneous CP. PEARL supports multiple CP interpreters and selects one for a new-joining agent in real time using two lightweight, multi-scale interpreters trained in parallel: a sparse-detection (LWSD) interpreter that aligns salient regions for cooperative detection, and a dense, domain-invariant (LWDDI) interpreter that produces agent-invariant features for fast interpreter selection. Both interpreters use low-rank visual prompts to reduce computation, storage, and model complexity. Extensive experiments on simulated (OPV2V, V2XSet) and real (DAIR-V2X) datasets show that PEARL generalizes across simulated and real-world cooperative driving scenarios. Its real-time model-selection strategy yields an 8.2% Average Precision (AP) gain over a random-selection baseline while running in 1.67 ms on average. Although primarily designed for real-time CP, PEARL also outperforms state-of-the-art heterogeneous CP frameworks under traditional offline training by 5.6% AP on average while reducing communication cost by up to 34.7 times. Equally important, PEARL does not require sharing agents' configurations or model settings, thereby protecting information that may be proprietary or private. These results establish PEARL as a scalable and practical framework for heterogeneous collaborative perception.