Guardado en:
| Autores principales: | , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2508.12684 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911109785583616 |
|---|---|
| author | Li, Zhongyao Cheng, Peirui Zhao, Liangjin Chen, Chen Li, Yundu Wang, Zhechao Yang, Xue Sun, Xian Wang, Zhirui |
| author_facet | Li, Zhongyao Cheng, Peirui Zhao, Liangjin Chen, Chen Li, Yundu Wang, Zhechao Yang, Xue Sun, Xian Wang, Zhirui |
| contents | Multi-UAV collaborative 3D detection enables accurate and robust perception by fusing multi-view observations from aerial platforms, offering significant advantages in coverage and occlusion handling, while posing new challenges for computation on resource-constrained UAV platforms. In this paper, we present AdaBEV, a novel framework that learns adaptive instance-aware BEV representations through a refine-and-contrast paradigm. Unlike existing methods that treat all BEV grids equally, AdaBEV introduces a Box-Guided Refinement Module (BG-RM) and an Instance-Background Contrastive Learning (IBCL) to enhance semantic awareness and feature discriminability. BG-RM refines only BEV grids associated with foreground instances using 2D supervision and spatial subdivision, while IBCL promotes stronger separation between foreground and background features via contrastive learning in BEV space. Extensive experiments on the Air-Co-Pred dataset demonstrate that AdaBEV achieves superior accuracy-computation trade-offs across model scales, outperforming other state-of-the-art methods at low resolutions and approaching upper bound performance while maintaining low-resolution BEV inputs and negligible overhead. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_12684 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Refine-and-Contrast: Adaptive Instance-Aware BEV Representations for Multi-UAV Collaborative Object Detection Li, Zhongyao Cheng, Peirui Zhao, Liangjin Chen, Chen Li, Yundu Wang, Zhechao Yang, Xue Sun, Xian Wang, Zhirui Computer Vision and Pattern Recognition Multi-UAV collaborative 3D detection enables accurate and robust perception by fusing multi-view observations from aerial platforms, offering significant advantages in coverage and occlusion handling, while posing new challenges for computation on resource-constrained UAV platforms. In this paper, we present AdaBEV, a novel framework that learns adaptive instance-aware BEV representations through a refine-and-contrast paradigm. Unlike existing methods that treat all BEV grids equally, AdaBEV introduces a Box-Guided Refinement Module (BG-RM) and an Instance-Background Contrastive Learning (IBCL) to enhance semantic awareness and feature discriminability. BG-RM refines only BEV grids associated with foreground instances using 2D supervision and spatial subdivision, while IBCL promotes stronger separation between foreground and background features via contrastive learning in BEV space. Extensive experiments on the Air-Co-Pred dataset demonstrate that AdaBEV achieves superior accuracy-computation trade-offs across model scales, outperforming other state-of-the-art methods at low resolutions and approaching upper bound performance while maintaining low-resolution BEV inputs and negligible overhead. |
| title | Refine-and-Contrast: Adaptive Instance-Aware BEV Representations for Multi-UAV Collaborative Object Detection |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2508.12684 |