Graph convolutional networks for learning with few clean and many noisy labels

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F20%3A00345902" target="_blank" >RIV/68407700:21230/20:00345902 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1007/978-3-030-58607-2_17" target="_blank" >https://doi.org/10.1007/978-3-030-58607-2_17</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-030-58607-2_17" target="_blank" >10.1007/978-3-030-58607-2_17</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Graph convolutional networks for learning with few clean and many noisy labels

Popis výsledku v původním jazyce

In this work we consider the problem of learning a classifier from noisy labels when a few clean labeled examples are given. The structure of clean and noisy data is modeled by a graph per class and Graph Convolutional Networks (GCN) are used to predict class relevance of noisy examples. For each class, the GCN is treated as a binary classifier, which learns to discriminate clean from noisy examples using a weighted binary cross-entropy loss function. The GCN-inferred “clean” probability is then exploited as a relevance measure. Each noisy example is weighted by its relevance when learning a classifier for the end task. We evaluate our method on an extended version of a few-shot learning problem, where the few clean examples of novel classes are supplemented with additional noisy data. Experimental results show that our GCNbased cleaning process significantly improves the classification accuracy over not cleaning the noisy data, as well as standard few-shot classification where only few clean examples are used.

Název v anglickém jazyce

Graph convolutional networks for learning with few clean and many noisy labels

Popis výsledku anglicky

In this work we consider the problem of learning a classifier from noisy labels when a few clean labeled examples are given. The structure of clean and noisy data is modeled by a graph per class and Graph Convolutional Networks (GCN) are used to predict class relevance of noisy examples. For each class, the GCN is treated as a binary classifier, which learns to discriminate clean from noisy examples using a weighted binary cross-entropy loss function. The GCN-inferred “clean” probability is then exploited as a relevance measure. Each noisy example is weighted by its relevance when learning a classifier for the end task. We evaluate our method on an extended version of a few-shot learning problem, where the few clean examples of novel classes are supplemented with additional noisy data. Experimental results show that our GCNbased cleaning process significantly improves the classification accuracy over not cleaning the noisy data, as well as standard few-shot classification where only few clean examples are used.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

Výsledek vznikl pri realizaci vícero projektů. Více informací v záložce Projekty.

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2020

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Computer Vision - ECCV 2020, Part X

ISBN

978-3-030-58606-5

ISSN

0302-9743

e-ISSN

1611-3349

Počet stran výsledku

17

Strana od-do

286-302

Název nakladatele

Springer International Publishing

Místo vydání

Cham

Místo konání akce

Glasgow

Datum konání akce

23. 8. 2020

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—