Carregant...
Tipus de document
Treball de fi de grauData de publicació
Llicència de publicació
Si us plau utilitzeu sempre aquest identificador per citar o enllaçar aquest document: https://hdl.handle.net/2445/187143
A class-conditional approach to learning with noisy labels
Títol de la revista
Autors
Director/Tutor
ISSN de la revista
Títol del volum
Recurs relacionat
Resum
[en] The main topic of this work is Learning with Noisy Labels (LNL). It is the field of Machine Learning concerned with training Neural Networks with noisy datasets. In particular, we have studied DivideMix, a method for LNL in the context of Computer Vision. After an extensive research we have discovered that it is unaware of the underlying class-conditional behaviour which consequently produces class imbalances. In this work, we present two class-conditional approaches to DivideMix. With this intent, we study approximate Baye-
sian Inference to quantify per-class uncertainty and leverage this extra information to improve the MixMatch step. In addition, we propose a class-aware policy that improves co-divide. Finally, improving DivideMix’s predictive accuracy by up to 0.39% in certain noise settings.
Descripció
Treballs Finals de Grau d'Enginyeria Informàtica, Facultat de Matemàtiques, Universitat de Barcelona, Any: 2022, Director: Petia Radeva
Citació
Citació
CATALÁN TATJER, Albert. A class-conditional approach to learning with noisy labels. [consulta: 20 de gener de 2026]. [Disponible a: https://hdl.handle.net/2445/187143]