HyDRA: Hybrid Domain-Aware Robust Architecture for Heterogeneous Collaborative Perception

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Song, Minwoo, Kang, Minhee, Ahn, Heejin
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866910070798811136
author Song, Minwoo
Kang, Minhee
Ahn, Heejin
author_facet Song, Minwoo
Kang, Minhee
Ahn, Heejin
contents In collaborative perception, an agent's performance can be degraded by heterogeneity arising from differences in model architecture or training data distributions. To address this challenge, we propose HyDRA (Hybrid Domain-Aware Robust Architecture), a unified pipeline that integrates intermediate and late fusion within a domain-aware framework. We introduce a lightweight domain classifier that dynamically identifies heterogeneous agents and assigns them to the late-fusion branch. Furthermore, we propose anchor-guided pose graph optimization to mitigate localization errors inherent in late fusion, leveraging reliable detections from intermediate fusion as fixed spatial anchors. Extensive experiments demonstrate that, despite requiring no additional training, HyDRA achieves performance comparable to state-of-the-art heterogeneity-aware CP methods. Importantly, this performance is maintained as the number of collaborating agents increases, enabling zero-cost scaling without retraining.
format Preprint
id arxiv_https___arxiv_org_abs_2603_23975
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle HyDRA: Hybrid Domain-Aware Robust Architecture for Heterogeneous Collaborative Perception
Song, Minwoo
Kang, Minhee
Ahn, Heejin
Computer Vision and Pattern Recognition
In collaborative perception, an agent's performance can be degraded by heterogeneity arising from differences in model architecture or training data distributions. To address this challenge, we propose HyDRA (Hybrid Domain-Aware Robust Architecture), a unified pipeline that integrates intermediate and late fusion within a domain-aware framework. We introduce a lightweight domain classifier that dynamically identifies heterogeneous agents and assigns them to the late-fusion branch. Furthermore, we propose anchor-guided pose graph optimization to mitigate localization errors inherent in late fusion, leveraging reliable detections from intermediate fusion as fixed spatial anchors. Extensive experiments demonstrate that, despite requiring no additional training, HyDRA achieves performance comparable to state-of-the-art heterogeneity-aware CP methods. Importantly, this performance is maintained as the number of collaborating agents increases, enabling zero-cost scaling without retraining.
title HyDRA: Hybrid Domain-Aware Robust Architecture for Heterogeneous Collaborative Perception
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.23975