Label Propagation for Deep Semi-supervised Learning

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F19%3A00335654" target="_blank" >RIV/68407700:21230/19:00335654 - isvavai.cz</a>

Výsledek na webu

<a href="https://ieeexplore.ieee.org/document/8954421" target="_blank" >https://ieeexplore.ieee.org/document/8954421</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/CVPR.2019.00521" target="_blank" >10.1109/CVPR.2019.00521</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Label Propagation for Deep Semi-supervised Learning

Popis výsledku v původním jazyce

Semi-supervised learning is becoming increasingly important because it can combine data carefully labeled by humans with abundant unlabeled data to train deep neural networks. Classic methods on semi-supervised learning that have focused on transductive learning have not been fully exploited in the inductive framework followed by modern deep learning. The same holds for the manifold assumption---that similar examples should get the same prediction. In this work, we employ a transductive label propagation method that is based on the manifold assumption to make predictions on the entire dataset and use these predictions to generate pseudo-labels for the unlabeled data and train a deep neural network. At the core of the transductive method lies a nearest neighbor graph of the dataset that we create based on the embeddings of the same network. Therefore our learning process iterates between these two steps. We improve performance on several datasets especially in the few labels regime and show that our work is complementary to current state of the art.

Název v anglickém jazyce

Label Propagation for Deep Semi-supervised Learning

Popis výsledku anglicky

Semi-supervised learning is becoming increasingly important because it can combine data carefully labeled by humans with abundant unlabeled data to train deep neural networks. Classic methods on semi-supervised learning that have focused on transductive learning have not been fully exploited in the inductive framework followed by modern deep learning. The same holds for the manifold assumption---that similar examples should get the same prediction. In this work, we employ a transductive label propagation method that is based on the manifold assumption to make predictions on the entire dataset and use these predictions to generate pseudo-labels for the unlabeled data and train a deep neural network. At the core of the transductive method lies a nearest neighbor graph of the dataset that we create based on the embeddings of the same network. Therefore our learning process iterates between these two steps. We improve performance on several datasets especially in the few labels regime and show that our work is complementary to current state of the art.

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

2019

Kód důvěrnosti údajů

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

Název statě ve sborníku

CVPR 2019: Proceedings of the 2019 IEEE Conference on Computer Vision and Pattern Recognition

ISBN

978-1-7281-3293-8

ISSN

1063-6919

e-ISSN

2575-7075

Počet stran výsledku

10

Strana od-do

5065-5074

Název nakladatele

IEEE

Místo vydání

—

Místo konání akce

Long Beach

Datum konání akce

15. 6. 2019

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—