首个实时旋转目标检测的Transformer模型，解决角度预测难题。
RiO-DETR: DETR for Real-time Oriented Object Detection
- 解耦角度与位置查询，用旋转校正注意力增强方向感知。
- 周期性精调机制稳定跨角度边界的学习，加速收敛。
- 密集监督注入角度多样性，提升速度与精度平衡，适合工业部署。
我们提出RiO-DETR：首个实时旋转目标检测的Transformer模型。将DETR适配到旋转边界框（OBB）面临三大挑战：语义依赖的方向性、角度周期性破坏标准欧氏优化、搜索空间扩大导致收敛变慢。RiO-DETR通过原生任务设计解决上述问题，同时保持实时效率。首先，提出内容驱动的角度估计，将角度从位置查询中解耦，并引入旋转校正正交注意力以捕捉互补线索，提升方向可靠性。其次，采用解耦周期性精调，结合有界粗到精更新与最短路径周期损失，实现跨角度缝合处的稳定学习。第三，引入面向旋转的密集O2O监督，以无额外成本注入角度多样性，加速角度收敛。在DOTA-1.0、DIOR-R和FAIR-1M-2.0数据集上的大量实验表明，RiO-DETR建立了实时旋转检测的新速度-精度权衡。开源地址：https://github.com/RicePasteM/RiO-DETR。
原文摘要 · Abstract (English)
We present RiO-DETR: DETR for Real-time Oriented Object Detection, the first real-time oriented detection transformer to the best of our knowledge. Adapting DETR to oriented bounding boxes (OBBs) poses three challenges: semantics-dependent orientation, angle periodicity that breaks standard Euclidean refinement, and an enlarged search space that slows convergence. RiO-DETR resolves these issues with task-native designs while preserving real-time efficiency. First, we propose Content-Driven Angle Estimation by decoupling angle from positional queries, together with Rotation-Rectified Orthogonal Attention to capture complementary cues for reliable orientation. Second, Decoupled Periodic Refinement combines bounded coarse-to-fine updates with a Shortest-Path Periodic Loss for stable learning across angular seams. Third, Oriented Dense O2O injects angular diversity into dense supervision to speed up angle convergence at no extra cost. Extensive experiments on DOTA-1.0, DIOR-R, and FAIR-1M-2.0 demonstrate RiO-DETR establishes a new speed--accuracy trade-off for real-time oriented detection. GitHub Repository: https://github.com/RicePasteM/RiO-DETR.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。