%0 Conference Proceedings
%T Class-conditional Importance Weighting for Deep Learning with Noisy Labels
%A Bhalaji Nagarajan
%A Ricardo Marques
%A Marcos Mejia
%A Petia Radeva
%B 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications
%D 2022
%V 5
%F Bhalaji Nagarajan2022
%O MILAB; no menciona
%O exported from refbase (http://158.109.8.37/show.php?record=3798), last updated on Mon, 24 Apr 2023 15:11:06 +0200
%X 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.
%K Noisy Labeling
%K Loss Correction
%K Class-conditional Importance Weighting
%K Learning with Noisy Labels
%U https://www.scitepress.org/Link.aspx?doi=10.5220/0010996400003124
%U http://dx.doi.org/10.5220/0010996400003124
%P 679-686