A Novel Multiple Instance Learning Method Based on Extreme Learning Machine

Table 1

ELM-MIL performance on benchmark data sets.

Algorithm	MUSK1	MUSK2	Elephant	Fox	Tiger
Iterated-discrim APR [1]	92.4	89.2	N/A	N/A	N/A
Citation-NN [14]	92.4	86.3	N/A	N/A	N/A
Diverse Density [13]	88	84	N/A	N/A	N/A
ELM-MIL (proposed)	86.5 (4.2)	85.8 (4.6)	76.7 (3.9)	59.5 (3.7)	74.6 (2.4)
EM-DD [3]	84.8	84.9	78.3	56.1	72.4
BP-MIP [16]	83.7	80.4	N/A	N/A	N/A
MI-SVM [8]	77.9	84.3	81.4	59.4	84
C4.5 [15]	68.5	58.5	N/A	N/A	N/A