We propose a multiple-kernel local-patch descriptor based on efficient match kernels from pixel gradients. It combines two parametrizations of gradient position and direction, each parametrization provides robustness to a different type of patch mis-registration: polar parametrization for noise in the patch dominant orientation detection, Cartesian for imprecise location of the feature point. Combined with whitening of the descriptor space, that is learned with or without supervision, the performance is significantly improved. We analyze the effect of the whitening on patch similarity and demonstrate its semantic meaning. Our unsupervised variant is the best performing descriptor constructed without the need of labeled data. Despite the simplicity of the proposed descriptor, it competes well with deep learning approaches on a number of different tasks.

中文翻译：

---

理解和改进内核本地描述符

我们提出了一种基于像素梯度的有效匹配内核的多内核局部补丁描述符。它结合了梯度位置和方向的两个参数化，每个参数化都为不同类型的补丁配准提供了鲁棒性：补丁主导方向检测中噪声的极坐标参数化，特征点不精确定位的笛卡尔参数化。结合描述符空间的白化，即在有监督或无监督的情况下学习，性能得到显着提高。我们分析了白化对补丁相似性的影响并证明了其语义。我们的无监督变体是在不需要标记数据的情况下构建的性能最佳的描述符。尽管提议的描述符很简单，