Deep Learning Classification With Noisy Labels

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Sanchez, Guillaume, Guis, Vincente, Marxer, Ricard, Bouchara, Frédéric
Natura: Preprint
Pubblicazione: 2020
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910600061255680
author Sanchez, Guillaume
Guis, Vincente
Marxer, Ricard
Bouchara, Frédéric
author_facet Sanchez, Guillaume
Guis, Vincente
Marxer, Ricard
Bouchara, Frédéric
contents Deep Learning systems have shown tremendous accuracy in image classification, at the cost of big image datasets. Collecting such amounts of data can lead to labelling errors in the training set. Indexing multimedia content for retrieval, classification or recommendation can involve tagging or classification based on multiple criteria. In our case, we train face recognition systems for actors identification with a closed set of identities while being exposed to a significant number of perturbators (actors unknown to our database). Face classifiers are known to be sensitive to label noise. We review recent works on how to manage noisy annotations when training deep learning classifiers, independently from our interest in face recognition.
format Preprint
id arxiv_https___arxiv_org_abs_2004_11116
institution arXiv
publishDate 2020
record_format arxiv
spellingShingle Deep Learning Classification With Noisy Labels
Sanchez, Guillaume
Guis, Vincente
Marxer, Ricard
Bouchara, Frédéric
Machine Learning
Deep Learning systems have shown tremendous accuracy in image classification, at the cost of big image datasets. Collecting such amounts of data can lead to labelling errors in the training set. Indexing multimedia content for retrieval, classification or recommendation can involve tagging or classification based on multiple criteria. In our case, we train face recognition systems for actors identification with a closed set of identities while being exposed to a significant number of perturbators (actors unknown to our database). Face classifiers are known to be sensitive to label noise. We review recent works on how to manage noisy annotations when training deep learning classifiers, independently from our interest in face recognition.
title Deep Learning Classification With Noisy Labels
topic Machine Learning
url https://arxiv.org/abs/2004.11116