Please use this identifier to cite or link to this item: https://doi.org/arXiv:1906.00562
DC FieldValue
dc.titleLearning to Self-Train for Semi-Supervised Few-Shot Classification
dc.contributor.authorXinzhe Li
dc.contributor.authorQianru Sun
dc.contributor.authorYaoyao Liu
dc.contributor.authorQin Zhou
dc.contributor.authorShibao Zheng
dc.contributor.authorTat-Seng Chua
dc.contributor.authorBernt Schiele
dc.date.accessioned2020-05-22T06:17:15Z
dc.date.available2020-05-22T06:17:15Z
dc.date.issued2019-12-08
dc.identifier.citationXinzhe Li, Qianru Sun, Yaoyao Liu, Qin Zhou, Shibao Zheng, Tat-Seng Chua, Bernt Schiele (2019-12-08). Learning to Self-Train for Semi-Supervised Few-Shot Classification. NeurIPS 2019. ScholarBank@NUS Repository. https://doi.org/arXiv:1906.00562
dc.identifier.urihttps://scholarbank.nus.edu.sg/handle/10635/168420
dc.description.abstractFew-shot classification (FSC) is challenging due to the scarcity of labeled training data (e.g. only one labeled data point per class). Meta-learning has shown to achieve promising results by learning to initialize a classification model for FSC. In this paper we propose a novel semi-supervised meta-learning method called learning to self-train (LST) that leverages unlabeled data and specifically metalearns how to cherry-pick and label such unsupervised data to further improve performance. To this end, we train the LST model through a large number of semi-supervised few-shot tasks. On each task, we train a few-shot model to predict pseudo labels for unlabeled data, and then iterate the self-training steps on labeled and pseudo-labeled data with each step followed by fine-tuning. We additionally learn a soft weighting network (SWN) to optimize the self-training weights of pseudo labels so that better ones can contribute more to gradient descent optimization. We evaluate our LST method on two ImageNet benchmarks for semi-supervised few-shot classification and achieve large improvements over the state-of-the-art method. Code is at github.com/xinzheli1217/learning-to-self-train.
dc.subjectFew-shot classification
dc.subjectdeep neural network
dc.subjectlearning to self-train
dc.typeConference Paper
dc.contributor.departmentDEPT OF COMPUTER SCIENCE
dc.contributor.departmentDEPT OF MATERIALS SCIENCE & ENGINEERING
dc.description.doiarXiv:1906.00562
dc.description.sourcetitleNeurIPS 2019
dc.grant.idR-252-300-002-490
dc.grant.fundingagencyInfocomm Media Development Authority
dc.grant.fundingagencyNational Research Foundation
Appears in Collections:Elements
Staff Publications

Show simple item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
Learning to Self-Train for Semi-Supervised Few-Shot Classification.pdf3.7 MBAdobe PDF

OPEN

NoneView/Download

Page view(s)

14
checked on Jul 9, 2020

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.