仅用一个点标注，快速精准检测旋转目标，速度超快且精度领先。
PointOBB-v2: Towards Simpler, Faster, and Stronger Single Point Supervised Oriented Object Detection
- 通过非均匀采样训练生成类别概率图，捕捉物体区域与轮廓。
- 用PCA分析概率图，准确估计目标方向和边界，密度高时仍稳定。
- 无需预训练模型或先验知识，适合密集场景，适合部署在资源受限环境。
单点监督的旋转目标检测受到关注并取得初步进展。不同于依赖一次性样本或强大预训练模型（如SAM）的方法，PointOBB因其无先验特征展现出潜力。本文提出PointOBB-v2，一种更简单、更快、更强的方法，仅从点生成伪旋转框，不依赖任何额外先验。首先，通过非均匀正负采样训练网络生成类别概率图（CPM），发现其能学习近似物体区域及其轮廓。随后，利用主成分分析（PCA）精确估计物体方向与边界。进一步引入分离机制，解决CPM中重叠导致的混淆问题，使其在高密度场景下仍可有效运行。大量实验表明，相比前代最优方法PointOBB，本方法在DOTA-v1.0/v1.5/v2.0数据集上分别实现15.58倍训练速度提升和11.60%/25.15%/21.19%的精度提升，显著推动了模块化单点监督旋转检测的前沿进展。
原文摘要 · Abstract (English)
Single point supervised oriented object detection has gained attention and made initial progress within the community. Diverse from those approaches relying on one-shot samples or powerful pretrained models (e.g. SAM), PointOBB has shown promise due to its prior-free feature. In this paper, we propose PointOBB-v2, a simpler, faster, and stronger method to generate pseudo rotated boxes from points without relying on any other prior. Specifically, we first generate a Class Probability Map (CPM) by training the network with non-uniform positive and negative sampling. We show that the CPM is able to learn the approximate object regions and their contours. Then, Principal Component Analysis (PCA) is applied to accurately estimate the orientation and the boundary of objects. By further incorporating a separation mechanism, we resolve the confusion caused by the overlapping on the CPM, enabling its operation in high-density scenarios. Extensive comparisons demonstrate that our method achieves a training speed 15.58x faster and an accuracy improvement of 11.60%/25.15%/21.19% on the DOTA-v1.0/v1.5/v2.0 datasets compared to the previous state-of-the-art, PointOBB. This significantly advances the cutting edge of single point supervised oriented detection in the modular track.
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。