arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2109.06148cs.CVcs.AIcs.LG
收藏

DAFNe:一种面向目标检测的一级无锚点方法

DAFNe: A One-Stage Anchor-Free Approach for Oriented Object Detection

TU Darmstadt(达姆施塔特工业大学);Hessian Center for AI and Centre for Cognitive Science(黑森人工智能中心与认知科学中心)

Steven Lang, Fabrizio Ventola, Kristian Kersting

摘要:

我们提出了DAFNe,一个面向目标检测的密集一级无锚深度网络。作为一个单阶段模型,它在输入图像上的密集网格上执行限界框预测,在设计上更简单,并且比两阶段模型更容易优化。此外,作为无锚模型,它通过避免使用限界框锚来降低预测复杂度。与DAFNe,我们引入了一个方向感知的泛化的任意方向的边界框的中心度函数,以降低权重低质量的预测和中心到角的限界框预测策略,提高对象定位性能。我们的实验表明,DAFNe在DOTA 1.0,DOTA 1.5和UCAS-AOD上的性能优于所有以前的一阶段无锚模型,并与HRSC 2016上的最佳模型相当。

英文摘要:

We present DAFNe, a Dense one-stage Anchor-Free deep Network for oriented object detection. As a one-stage model, it performs bounding box predictions on a dense grid over the input image, being architecturally simpler in design, as well as easier to optimize than its two-stage counterparts. Furthermore, as an anchor-free model, it reduces the prediction complexity by refraining from employing bounding box anchors. With DAFNe we introduce an orientation-aware generalization of the center-ness function for arbitrarily oriented bounding boxes to down-weight low-quality predictions and a center-to-corner bounding box prediction strategy that improves object localization performance. Our experiments show that DAFNe outperforms all previous one-stage anchor-free models on DOTA 1.0, DOTA 1.5, and UCAS-AOD and is on par with the best models on HRSC2016.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑