Stochastic mean-shift clustering

It estimates the probability density function of a random variable Fukunaga & Hostetler (1975). The clustering algorithm is applied to a variety of areas, like segmentation images, Tao et al. (2007); Paris & Durand (2007), particularly medical and satellite images Lu et al. (2011); Ai & Xiong (2014); Wu & Luo (2015); Banerjee et al. (2012), videos Wang et al. (2004), and also applied to high dimensional data clustering Saptarshi et al. (2021). An adapted version of mean-shift clustering was applied to short segments speaker clustering Salmun et al. (2016b,a, 2017); Cohen & Lapidot (2021). This algorithm is deterministic and in an iterative procedure estimates the multi-modal probability density function (pdf) via the "climbing" path of each datum to its mode in a multi-modal distribution. All the data points that reached the same mode are grouped to the same cluster.