Table 1.

Best Rand and information theoretic scores of all teams and the human experts using the undisclosed test set at ISBI.

Method	VRand	VInfo
Human 1 vs. consensus	0.997 ± 0.001	0.997 ± 0.001
human 2 vs. consensus	0.971 ± 0.003	0.941 ± 0.002
IDSIA	0.944 ± 0.011	0.968 ± 0.002
BlackEagles	0.929 ± 0.008	0.916 ± 0.003
MLL-ETH	0.927 ± 0.008	0.923 ± 0.004
SCI	0.915 ± 0.016	0.967 ± 0.003
CellProfiler	0.904 ± 0.015	0.937 ± 0.006
Harvard	0.892 ± 0.017	0.947 ± 0.004
CoMPLEX	0.877 ± 0.019	0.903 ± 0.008
UCL	0.860 ± 0.020	0.939 ± 0.005
TSC+PP	0.843 ± 0.012	0.838 ± 0.006
IMMI	0.826 ± 0.022	0.862 ± 0.008
CLP	0.809 ± 0.018	0.846 ± 0.005
Freiburg	0.800 ± 0.026	0.825 ± 0.005
NIST	0.730 ± 0.021	0.757 ± 0.007

Mean and standard error are computed over 20 test images not used for the public leaderboard.