BriefGPT.xyz
Jun, 2018
一种概率约束聚类方法用于迁移学习和图像类别发现
A probabilistic constrained clustering for transfer learning and image category discovery
HTML
PDF
Yen-Chang Hsu, Zhaoyang Lv, Joel Schlosser, Phillip Odom, Zsolt Kira
TL;DR
本研究提出了一种针对深度网络和大量类别进行优化的聚类目标函数，通过对成对约束条件的负对数似然最小化来优化聚类分配，具有优秀的可扩展性和性能。
Abstract
neural network-based clustering
has recently gained popularity, and in particular a
constrained clustering
formulation has been proposed to perform
→