19 citations · 23 across the 2 of their papers we have counts for
2 papers
cs.LG2021★ 19 cited
MetaLabelNet: Learning to Generate Soft-Labels from Noisy-Labels
Görkem Algan, Ilkay Ulusoy
Real-world datasets commonly have noisy labels, which negatively affects the performance of deep neural networks (DNNs). In order to address this problem, we propose a label noise…
cs.CV2020★ 4 cited
Deep Learning from Small Amount of Medical Data with Noisy Labels: A Meta-Learning Approach
Görkem Algan, Ilkay Ulusoy, Şaban Gönül +2
Computer vision systems recently made a big leap thanks to deep neural networks. However, these systems require correctly labeled large datasets in order to be trained properly, wh…