id	author	title	date	pages	extension	mime	words	sentence	flesch	summary	cache	txt
dpc-1863	Katsch, Florian; Rinner, Christoph; Tschandl, Philipp	Comparison of convolutional neural network architectures for robustness against common artefacts in dermatoscopic images	2022	7	.pdf	application/pdf	3635	299	59	The HAM10000-dataset with and without superimposed artefacts was used to train the networks, followed by analyzing their robustness against artefacts in test images. The influence on classi- fication results by artefacts in test images can be reduced by augmenting training data with artificially superimposed arte- facts for all three architectures.	cache/dpc-1863.pdf	txt/dpc-1863.txt