Supervised and self-supervised DNNs for skin lesion classification generalize poorly to acral lesions on black skin compared with white skin.
Evaluating deep neural networks trained on clinical images in dermatology with the fitzpatrick 17k dataset
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2023 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Assessing the Generalizability of Deep Neural Networks-Based Models for Black Skin Lesions
Supervised and self-supervised DNNs for skin lesion classification generalize poorly to acral lesions on black skin compared with white skin.