@InProceedings{BhalajiNagarajan2022,
author="Bhalaji Nagarajan
and Ricardo Marques
and Marcos Mejia
and Petia Radeva",
title="Class-conditional Importance Weighting for Deep Learning with Noisy Labels",
booktitle="17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications",
year="2022",
volume="5",
pages="679--686",
optkeywords="Noisy Labeling",
optkeywords="Loss Correction",
optkeywords="Class-conditional Importance Weighting",
optkeywords="Learning with Noisy Labels",
abstract="Large-scale accurate labels are very important to the Deep Neural Networks to train them and assure high performance. However, it is very expensive to create a clean dataset since usually it relies on human interaction. To this purpose, the labelling process is made cheap with a trade-off of having noisy labels. Learning with Noisy Labels is an active area of research being at the same time very challenging. The recent advances in Self-supervised learning and robust loss functions have helped in advancing noisy label research. In this paper, we propose a loss correction method that relies on dynamic weights computed based on the model training. We extend the existing Contrast to Divide algorithm coupled with DivideMix using a new class-conditional weighted scheme. We validate the method using the standard noise experiments and achieved encouraging results.",
optnote="MILAB; no menciona",
optnote="exported from refbase (http://158.109.8.37/show.php?record=3798), last updated on Mon, 24 Apr 2023 15:11:06 +0200",
doi="10.5220/0010996400003124",
opturl="https://www.scitepress.org/Link.aspx?doi=10.5220/0010996400003124"
}