Self-Supervised Learning to Increase the Performance of Skin Lesion Classification - Publikacja - MOST Wiedzy


Self-Supervised Learning to Increase the Performance of Skin Lesion Classification


To successfully train a deep neural network, a large amount of human-labeled data is required. Unfortunately, in many areas, collecting and labeling data is a difficult and tedious task. Several ways have been developed to mitigate the problem associated with the shortage of data, the most common of which is transfer learning. However, in many cases, the use of transfer learning as the only remedy is insufficient. In this study, we improve deep neural models training and increase the classification accuracy under a scarcity of data by the use of the self-supervised learning technique. Self-supervised learning allows an unlabeled dataset to be used for pretraining the network, as opposed to transfer learning that requires labeled datasets. The pretrained network can be then fine-tuned using the annotated data. Moreover, we investigated the effect of combining the self-supervised learning approach with transfer learning. It is shown that this strategy outperforms network training from scratch or with transfer learning. The tests were conducted on a very important and sensitive application (skin lesion classification), but the presented approach can be applied to a broader family of applications, especially in the medical domain where the scarcity of data is a real problem.


  • 1


  • 1

    Web of Science

  • 1


Cytuj jako

Pełna treść

pobierz publikację
pobrano 16 razy
Wersja publikacji
Accepted albo Published Version
Creative Commons: CC-BY otwiera się w nowej karcie

Słowa kluczowe

Informacje szczegółowe

Publikacja w czasopiśmie
artykuły w czasopismach
Opublikowano w:
Electronics nr 9,
ISSN: 2079-9292
Rok wydania:
Opis bibliograficzny:
Kwasigroch A., Grochowski M., Mikołajczyk A.: Self-Supervised Learning to Increase the Performance of Skin Lesion Classification// Electronics -Vol. 9,iss. 11 (2020), s.1930-
Cyfrowy identyfikator dokumentu elektronicznego (otwiera się w nowej karcie) 10.3390/electronics9111930
Politechnika Gdańska

wyświetlono 44 razy

Publikacje, które mogą cię zainteresować

Meta Tagi