Retinal Vessel Segmentation for Retinography

		driu	hed	m2unet	unet	lwnet
Dataset	2nd. Annot.	15M	14.7M	550k	25.8M	68k
drive	0.788 (0.021)	0.821 (0.014)	0.813 (0.016)	0.802 (0.014)	0.825 (0.015)	0.828
stare	0.759 (0.028)	0.828 (0.039)	0.815 (0.047)	0.818 (0.035)	0.828 (0.050)	0.839
chasedb1	0.768 (0.023)	0.812 (0.018)	0.806 (0.020)	0.798 (0.018)	0.807 (0.017)	0.820
hrf (1168x1648)		0.808 (0.038)	0.803 (0.040)	0.796 (0.048)	0.811 (0.039)	0.814
hrf (2336x3296)		0.722 (0.073)	0.703 (0.090)	0.713 (0.143)	0.756 (0.051)	0.744
iostar-vessel		0.825 (0.020)	0.827 (0.020)	0.820 (0.018)	0.818 (0.020)	0.832

Notes

• HRF models were trained using half the full resolution (1168x1648)

• The following table describes recommended batch sizes for 24Gb of RAM GPU card:

	driu	hed	m2unet	unet	lwnet
drive	8	8	16	4	4
stare	5	4	6	2	4
chasedb1	4	4	6	2	4
hrf	1	1	1	1	4
iostar-vessel	4	4	6	2	4

Results for datasets with (768x768 resolution)

		driu	hed	m2unet	unet	lwnet
Dataset	2nd. Annot.	15M	14.7M	550k	25.8M	68k
drive		0.812	0.806	0.800	0.814	0.807
stare		0.819	0.812	0.793	0.829	0.817
chasedb1		0.809	0.790	0.793	0.803	0.797
hrf		0.799	0.774	0.773	0.804	0.800
iostar-vessel		0.825	0.818	0.813	0.820	0.820
Combined datasets		0.811	0.798	0.798	0.813	0.804

Notes

• The following table describes recommended batch sizes for 24Gb of RAM GPU card:

	driu	hed	m2unet	unet	lwnet
drive	8	8	8	4	8
stare	8	8	8	4	8
chasedb1	8	8	8	4	8
hrf	8	8	8	4	8
iostar-vessel	8	8	8	4	8

Results for datasets with (1024x1024 resolution)

		driu	hed	m2unet	unet	lwnet
Dataset	2nd. Annot.	15M	14.7M	550k	25.8M	68k
drive		0.813	0.806	0.804	0.815	0.809
stare		0.821	0.812	0.816	0.820	0.814
chasedb1		0.806	0.806	0.790	0.806	0.793
hrf		0.805	0.793	0.786	0.807	0.805
iostar-vessel		0.829	0.825	0.817	0.825	0.824

Notes

• The following table describes recommended batch sizes for 24Gb of RAM GPU card:

	driu	hed	m2unet	unet	lwnet
drive	8	8	8	4	8
stare	8	8	8	4	8
chasedb1	8	8	8	4	8
hrf	8	8	8	4	8
iostar-vessel	8	8	8	4	8