BriefGPT.xyz
Jul, 2018
深度聚类用于视觉特征无监督学习
Deep Clustering for Unsupervised Learning of Visual Features
HTML
PDF
Mathilde Caron, Piotr Bojanowski, Armand Joulin, Matthijs Douze
TL;DR
本文介绍了DeepCluster，一种聚类方法，它能够联合学习神经网络的参数和聚类分配，并应用于卷积神经网络在大型数据集上的无监督训练，取得了显著的性能提升。
Abstract
clustering
is a class of
unsupervised learning
methods that has been extensively applied and studied in computer vision. Little work has been done to adapt it to the end-to-end training of visual features on larg
→