BMC Medical Imaging

Table 13 Results on the validation data set considering different dropout rates

From: Automated classification of polyps using deep learning architectures and few-shot learning

Model		Dropout rate		Val-acc
	0.4	0.5	0.6
EfficientNet-B7	\(\checkmark\)			0.8094
		\(\checkmark\)		0.8212
			\(\checkmark\)	0.7908
Ours	\(\checkmark\)			0.8593
		\(\checkmark\)		0.8950
			\(\checkmark\)	0.8513

Bold values are indicating the highest value of a column for the given model
BiT-R152x4 did not use dropout and is therefore not included in this table

Back to article page

ISSN: 1471-2342

Contact us

General enquiries: journalsubmissions@springernature.com