Bildverarbeitung für die Medizin 2019 pp 199-199 | Cite as
Abstract: Leveraging Web Data for Skin Lesion Classification
Conference paper
First Online:
Zusammenfassung
The success of deep learning is mainly based on the assumption that for the given application, there is access to a large amount of annotated data. In medical imaging applications, having access to a big-well-annotated data-set is restrictive, time-consuming and costly to obtain. Although diverse techniques as data augmentation can be leveraged to increase the size and variability within the data-set, the representativeness of the training set is still limited by the number of available samples.
Download
to read the full conference paper text
Literatur
- 1.Navarro F, Conjeti S, Tombari F, et al. Webly supervised learning for skin lesion classification. Proc MICCAI. 2018; p. 398–406.Google Scholar
- 2.Chen X, Gupta A. Webly supervised learning of convolutional networks. Proc CVPR. 2015; p. 1431–1439.Google Scholar
- 3.Patrini G, Rozza A, Menon AK, et al. Making deep neural networks robust to label noise: a loss correction approach. Proc CVPR. 2017; p. 2233–2241.Google Scholar
Copyright information
© Springer Fachmedien Wiesbaden GmbH, ein Teil von Springer Nature 2019