Metraipolis › archive › dc_91cebdbcdf46
TADP: Task-Aware Deformable Prediction for Single-Stage 3D Object Detection — arXiv:2608.27282
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.27282
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T14:30:46.890Z
- SHA-256 of the archived text
01029b65f74accb545360697833c9b138d22e48492600b790cc83bc69b30f659- Stable URL of this page
https://metraipolis.com/documento/dc_91cebdbcdf46
How to cite
TADP: Task-Aware Deformable Prediction for Single-Stage 3D Object Detection — arXiv:2608.27282 — arXiv (en), https://arxiv.org/abs/2608.27282 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_91cebdbcdf46 (Metraipolis archive dc_91cebdbcdf46, sha256 01029b65f74accb545360697833c9b138d22e48492600b790cc83bc69b30f659)
BibTeX
@misc{dc91cebdbcdf46,
title = {TADP: Task-Aware Deformable Prediction for Single-Stage 3D Object Detection — arXiv:2608.27282},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.27282},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_91cebdbcdf46; sha256 01029b65f74accb545360697833c9b138d22e48492600b790cc83bc69b30f659},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.27282. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Most single-stage 3D object detectors complete different tasks with the same extracted features. Nevertheless, it is impossible to project features into a common space that is adaptive for all the tasks. We present a novel task-aware deformable prediction (TADP) method for single-stage 3D object detection to solve this problem. Firstly, a triple feature refinement aggregation module is designed to extract three-level features adaptively. Additionally, we design the multi-scale feature aggregation block to fuse multi-scale features in a scale-aware manner. Finally, the prediction of each task is deformed with the designed plug-and-play task-aware deformation head. It can percept the emphasis and interaction of each task. We also designed three different deformation modules. The experimental results demonstrate that the proposed deformation head shows good results on other detection methods. The experimental results on the KITTI dataset demonstrate that the car mAP is 80.91%, surpassing many state-of-the-art methods on the KITTI benchmark. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-28 in cs.AI). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI); Robotics (cs.RO); Systems and Control (eess.SY). Pagina del lavoro: https://arxiv.org/abs/2608.27282 — 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 2026-10-17T13:16:53.704Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).