Skip to main content

Table 1 The average segmentation accuracies obtained with LOCUS [ [8]], ClassCut [ [9]], Arora et al. [ [10]], BiCos [ [18]] and our method over the Weizmann horses and Caltech-4 datasets

From: A hierarchical graph model for object cosegmentation

Method

Weizmann horses

Caltech airplane

Caltech face

Caltech motorbike

LOCUS [8]

0.931

-

-

-

ClassCut [9]

0.862

0.888

0.890

0.903

Arora et al. [10]

-

0.931

0.924

0.831

BiCos [18]

0.900

0.932

0.911

0.822

Our method

0.884

0.943

0.921

0.878

  1. The values in bold indicate the best results.