基于深度特征表示的Softmax聚类算法
陈俊芬,赵佳成,韩洁,翟俊海

Softmax clustering algorithm based on deep features representation
Junfen Chen,Jiacheng Zhao,Jie Han,Junhai Zhai
表2 在MNIST数据集上比较ASCAE,ASCAE?Softmax和六个聚类算法的聚类性能
Table 2 Clustering performances of ASCAE,ASCAE?Softmax and other six clustering algorithms on MNIST dataset

Algorithms

ACC

NMI

KMS[6]

0.535

0.531

AEC[6]

0.760

0.669

IEC[6]

0.609

0.542

DEC

0.889

0.856

DBC

0.766

0.759

DEPICT

0.924

0.850

ASCAE

0.925

0.854

ASCAE?Softmax

0.960

0.910