基于Kullback-Leibler发散的高精度旋转目标检测限界框
Learning High-Precision Bounding Box for Rotated Object Detection via Kullback-Leibler Divergence
摘要：
现有的旋转对象检测器大多继承自水平检测范式，因为后者已经发展成为一个成熟的领域。然而，由于当前回归损失设计的限制，这些检测器很难在高精度检测中表现突出，特别是对于具有大纵横比的对象。基于水平检测是旋转目标检测的一个特例的观点，根据旋转与水平检测的关系，将旋转回归损失的设计从归纳范式转变为演绎方法。我们发现，一个重要的挑战是如何调制的旋转回归损失的耦合参数，这样的估计参数可以相互影响，在动态联合优化，在自适应和协同的方式。具体来说，我们首先将旋转的限界框转换为2-D高斯分布，然后计算高斯分布之间的Kullback-Leibler散度（KLD）作为回归损失。通过分析每个参数的梯度，我们表明，KLD（及其衍生物）可以动态调整参数梯度根据对象的特性。它将根据纵横比调整角度参数的重要性（梯度权重）。这种机制对于高精度检测至关重要，因为微小的角度误差会导致大纵横比物体的精度严重下降。更重要的是，我们证明了KLD是尺度不变的。我们进一步表明，KLD损失可以退化成流行的$l_{n}$ -范数损失水平检测。使用不同检测器在七个数据集上进行的实验结果表明了其一致的优越性，代码可在https://github.com/yangxue0827/RotationDetection和https://github.com/open-mmlab/mmrotate上获得。
英文摘要：
Existing rotated object detectors are mostly inherited from the horizontal detection paradigm, as the latter has evolved into a well-developed area. However, these detectors are difficult to perform prominently in high-precision detection due to the limitation of current regression loss design, especially for objects with large aspect ratios. Taking the perspective that horizontal detection is a special case for rotated object detection, in this paper, we are motivated to change the design of rotation regression loss from induction paradigm to deduction methodology, in terms of the relation between rotation and horizontal detection. We show that one essential challenge is how to modulate the coupled parameters in the rotation regression loss, as such the estimated parameters can influence to each other during the dynamic joint optimization, in an adaptive and synergetic way. Specifically, we first convert the rotated bounding box into a 2-D Gaussian distribution, and then calculate the Kullback-Leibler Divergence (KLD) between the Gaussian distributions as the regression loss. By analyzing the gradient of each parameter, we show that KLD (and its derivatives) can dynamically adjust the parameter gradients according to the characteristics of the object. It will adjust the importance (gradient weight) of the angle parameter according to the aspect ratio. This mechanism can be vital for high-precision detection as a slight angle error would cause a serious accuracy drop for large aspect ratios objects. More importantly, we have proved that KLD is scale invariant. We further show that the KLD loss can be degenerated into the popular $l_{n}$-norm loss for horizontal detection. Experimental results on seven datasets using different detectors show its consistent superiority, and codes are available at https://github.com/yangxue0827/RotationDetection and https://github.com/open-mmlab/mmrotate.
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。
