Login (DCU Staff Only)
Login (DCU Staff Only)

DORAS | DCU Research Repository

Explore open access research and scholarly works from DCU

Advanced Search

ReLaB: reliable label bootstrapping for semi-supervised learning

Albert, Paul, Ortego, Diego orcid logoORCID: 0000-0002-1011-3610, Arazo, Eric, O'Connor, Noel E. orcid logoORCID: 0000-0002-4033-9135 and McGuiness, Kevin orcid logoORCID: 0000-0003-1336-6477 (2021) ReLaB: reliable label bootstrapping for semi-supervised learning. In: International Joint Conference on Neural Networls (IJCNN), 18-22 July 2021, Shenzhen, China (Online).

Abstract
Reducing the amount of labels required to train convolutional neural networks without performance degradation is key to effectively reduce human annotation efforts. We propose Reliable Label Bootstrapping (ReLaB), an unsupervised preprossessing algorithm which improves the performance of semi-supervised algorithms in extremely low supervision settings. Given a dataset with few labeled samples, we first learn meaningful self-supervised, latent features for the data. Second, a label propagation algorithm propagates the known labels on the unsupervised features, effectively labeling the full dataset in an automatic fashion. Third, we select a subset of correctly labeled (reliable) samples using a label noise detection algorithm. Finally, we train a semi-supervised algorithm on the extended subset. We show that the selection of the network architecture and the self-supervised algorithm are important factors to achieve successful label propagation and demonstrate that ReLaB substantially improves semi-supervised learning in scenarios of very limited supervision on image classification benchmarks such as CIFAR-10, CIFAR-100 and mini-ImageNet. We reach average error rates of 22.34 with 1 random labeled sample per class on CIFAR-10 and lower this error to 8.46 when the labeled sample in each class is highly representative. Our work is fully reproducible: https://github.com/PaulAlbert31/ReLaB.
Metadata
Item Type:Conference or Workshop Item (Paper)
Event Type:Conference
Refereed:Yes
Subjects:Computer Science > Artificial intelligence
Computer Science > Image processing
Computer Science > Machine learning
DCU Faculties and Centres:DCU Faculties and Schools > Faculty of Engineering and Computing > School of Electronic Engineering
Research Initiatives and Centres > INSIGHT Centre for Data Analytics
Published in: 2021 International Joint Conference on Neural Networks (IJCNN). . IEEE.
Publisher:IEEE
Official URL:https://doi.org/10.1109/IJCNN52387.2021.9533616
Copyright Information:© 2021 The Authors
Use License:This item is licensed under a Creative Commons Attribution-NonCommercial-Share Alike 3.0 License. View License
Funders:Insight, Science Foundation Ireland (SFI) under grant number [SFI/15/SIRG/3283], Science Foundation Ireland (SFI) under grant number [SFI/12/RC/2289P2], Department of Agriculture, Food and Marine on behalf of the Government of Ireland under Grant Number [16/RC/3835]
ID Code:25767
Deposited On:19 Jul 2021 08:37 by Paul Albert . Last Modified 04 Nov 2021 15:07
Documents

Full text available as:

[thumbnail of ReLaB_IJCNN_2021__Noel_Hosted_.pdf]
Preview
PDF - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
404kB
[thumbnail of ReLaB_IJCNN_2021__Noel_Hosted_(1).pdf]
Preview
PDF - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
1MB
Downloads

Downloads

Downloads per month over past year

Archive Staff Only: edit this record