Metraipolis › archive › dc_09bde830b986
PEARL: A Lightweight Prompt-based Feature Interpreter Framework for Real-Time, Anonymous, and Heterogeneous Collaborative Perception — arXiv:2609.27123
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.27123
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T10:57:52.869Z
- SHA-256 of the archived text
e92e2934c2061f0ebbe2640c732d2b3bbf3ec961dc5fed222bd538ca2c2c068f- Stable URL of this page
https://metraipolis.com/documento/dc_09bde830b986
How to cite
PEARL: A Lightweight Prompt-based Feature Interpreter Framework for Real-Time, Anonymous, and Heterogeneous Collaborative Perception — arXiv:2609.27123 — arXiv (en), https://arxiv.org/abs/2609.27123 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_09bde830b986 (Metraipolis archive dc_09bde830b986, sha256 e92e2934c2061f0ebbe2640c732d2b3bbf3ec961dc5fed222bd538ca2c2c068f)
BibTeX
@misc{dc09bde830b986,
title = {PEARL: A Lightweight Prompt-based Feature Interpreter Framework for Real-Time, Anonymous, and Heterogeneous Collaborative Perception — arXiv:2609.27123},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.27123},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_09bde830b986; sha256 e92e2934c2061f0ebbe2640c732d2b3bbf3ec961dc5fed222bd538ca2c2c068f},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.27123. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-24 in cs.LG). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.27123 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-08T10:06:16.801Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).