PT Unknown
AU Bhalaji Nagarajan
   Ricardo Marques
   Marcos Mejia
   Petia Radeva
TI Class-conditional Importance Weighting for Deep Learning with Noisy Labels
BT 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications
PY 2022
BP 679
EP 686
VL 5
DI 10.5220/0010996400003124
DE Noisy Labeling; Loss Correction; Class-conditional Importance Weighting; Learning with Noisy Labels
AB 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.
ER