论文阅读 [TPAMI-2022] Ball kkkk-Means: Fast Adaptive Clustering With No Bounds

论文搜索(studyai.com)

搜索论文: Ball kkkk-Means: Fast Adaptive Clustering With No Bounds

搜索论文: http://www.studyai.com/search/whole-site/?q=Ball+kkkk-Means:+Fast+Adaptive+Clustering+With+No+Bounds

关键字(Keywords)

Clustering algorithms; Approximation algorithms; Acceleration; Partitioning algorithms; Standards; Laboratories; Time complexity; Ball kkk k -means; ** kkk k -means**; ball cluster; stable area; active area; neighbor cluster

机器学习

聚类

摘要(Abstract)

This paper presents a novel accelerated exact kkkk-means called as “Ball kkkk-means” by using the ball to describe each cluster, which focus on reducing the point-centroid distance computation.

本文提出了一种新的加速精确kkkk-均值算法，称为“Ballkkkk-means”，该算法使用球来描述每个簇，其重点是减少点质心距离的计算。.

The “Ball kkkk-means” can exactly find its neighbor clusters for each cluster, resulting distance computations only between a point and its neighbor clusters’ centroids instead of all centroids.

“Ballkkkk-means”可以精确地为每个簇找到其相邻簇，从而只计算一个点与其相邻簇的质心之间的距离，而不是所有质心之间的距离。.

What’s more, each cluster can be divided into “stable area” and “active area”, and the latter one is further divided into some exact “annular area”.

此外，每个星团可分为“稳定区”和“活动区”，后者又可进一步分为一些精确的“环形区”。.

The assignment of the points in the “stable area” is not changed while the points in each “annular area” will be adjusted within a few neighbor clusters.

“稳定区域”中的点的分配不变，而每个“环形区域”中的点将在几个相邻簇内进行调整。.

There are no upper or lower bounds in the whole process.

整个过程没有上限或下限。.

Moreover, ball kkkk-means uses ball clusters and neighbor searching along with multiple novel stratagems for reducing centroid distance computations.

此外，ballkkkk-means使用球簇和邻居搜索以及多种新策略来减少质心距离计算。.

In comparison with the current state-of-the art accelerated exact bounded methods, the Yinyang algorithm and the Exponion algorithm, as well as other top-of-the-line tree-based and bounded methods, the ball kkkk-means attains both higher performance and performs fewer distance calculations, especially for large-k problems.

与当前最先进的加速精确有界方法、阴阳算法和指数算法，以及其他基于顶层树和有界方法相比，ballkkkk-means既获得了更高的性能，也执行了更少的距离计算，尤其是对于大k问题。.

The faster speed, no extra parameters and simpler design of “Ball kkkk-means” make it an all-around replacement of the naive kkkk-means…

“Ballkkkk-means”的更快速度、无额外参数和更简单的设计使其成为天真的kkkk-means的全面替代品。。.

作者(Authors)

[‘Shuyin Xia’, ‘Daowan Peng’, ‘Deyu Meng’, ‘Changqing Zhang’, ‘Guoyin Wang’, ‘Elisabeth Giem’, ‘Wei Wei’, ‘Zizhong Chen’]

论文阅读 [TPAMI-2022] Ball $k$k-Means: Fast Adaptive Clustering With No Bounds相关推荐

论文阅读11——《Mutual Boost Network for Attributed Graph Clustering》
是聚类让我们"聚类",我整理了部分深度图聚类代码,希望大家多多支持(GitHub代码):A-Unified-Framework-for-Deep-Attribute-Graph-C ...
【论文阅读】22-GMS: Grid-based Motion Statistics for Fast, Ultra-robust Feature Correspondence
[论文阅读]22-GMS: Grid-based Motion Statistics for Fast, Ultra-robust Feature Correspondence 0.basic inf ...
论文阅读笔记（8）：Structured Sparse Subspace Clustering: A Joint Affinity Learning and Subspace Clustering
论文阅读笔记(8):Structured Sparse Subspace Clustering: A Joint Affinity Learning and Subspace Clustering F ...
（论文阅读）2022年一些图像去雾方法的简单调研
2022年一些图像去雾方法的简单调研 1. Self-augmented Unpaired Image Dehazing via Density and Depth Decomposition 基于密 ...
【论文阅读 NeurIPS 2022】A Large Scale Search Dataset for Unbiased Learning to Rank
文章目录前言 Abs Intro 2.Preliminary 2.1.Ubiased Learning to Rank 2.2.Existion ULTR Datasets 3.Dataset De ...
【论文阅读笔记|ACL2022】Continual Sequence Generation with Adaptive Compositional Modules
论文题目:Continual Sequence Generation with Adaptive Compositional Modules 论文来源:ACL2022 论文链接:https://acl ...
论文阅读（XiangBai——【AAAI2017】TextBoxes_A Fast Text Detector with a Single Deep Neural Network）...
XiangBai--[AAAI2017]TextBoxes:A Fast Text Detector with a Single Deep Neural Network 目录作者和相关链接方法概括 ...
【论文阅读】【3d目标检测】FAST pointrcnn
论文标题:Fast Point R-CNN 还是记录... 这篇文章后面与voxelnet进行了fps对比,究竟快在哪里,究竟为啥ap提升了?是本文想要探讨的东西. 文章的思路很简单,分为两个阶段第 ...
[论文阅读]IDM: An Intermediate Domain Module for Domain Adaptive Person Re-ID (ICCV2021)
IDM: An Intermediate Domain Module for Domain Adaptive Person Re-ID (ICCV2021) 一种基于中间域的域自适应行人重识别领域: ...

论文阅读 [TPAMI-2022] Ball $k$k-Means: Fast Adaptive Clustering With No Bounds