Carregant...
Miniatura

Tipus de document

Treball de fi de grau

Data de publicació

Llicència de publicació

memòria: cc-nc-nd (c) Albert Catalán Tatjer, 2022
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

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]

Exportar metadades

JSON - METS

Compartir registre