Benchmark Results

F1 Scores

  • Benchmark results for models: DRIU, HED, M2UNet and U-Net.

  • Models are trained and tested on the same dataset using the train-test split as indicated in Supported Datasets

  • Standard-deviations across all test images are indicated in brakets

F1 (std)

CHASEDB1

DRIVE

HRF

IOSTARVESSEL

STARE

DRIU

0.810 (0.021)

0.820 (0.014)

0.783 (0.055)

0.825 (0.020)

0.827 (0.037)

HED

0.810 (0.022)

0.817 (0.013)

0.783 (0.058)

0.825 (0.020)

0.823 (0.037)

M2UNet

0.802 (0.019)

0.803 (0.014)

0.780 (0.057)

0.817 (0.020)

0.815 (0.041)

UNet

0.812 (0.020)

0.822 (0.015)

0.788 (0.051)

0.818 (0.019)

0.829 (0.042)