Evaluation Results overaged ver the whole Benchmark under different numSegments settings

We show the evaluation results in four metrics under the following six alternative ways to set numSegments:
figures/RIbyLevel.png
Rand Index
figures/CDbyLevel.png
Cut Discrepancy
figures/GCEbyLevel.png
Global Consistency Error
figures/LCEbyLevel.png
Local Consistency Error
figures/HDbyLevel.png
Hamming Distance
figures/HD-RmbyLevel.png
Hamming Distance - Missing Rate
figures/HD-RfbyLevel.png
Hamming Distance - False Alarm Rate