Show simple item record

dc.contributor.authorLiu, Junyu
dc.contributor.authorLi, Xiang
dc.contributor.authorZhou, Jiqiang
dc.contributor.authorShen, Jianxiong
dc.contributor.otherUniversitat Politècnica de Catalunya. Doctorat en Automàtica, Robòtica i Visió
dc.date.accessioned2021-02-17T10:36:37Z
dc.date.issued2020
dc.identifier.citationLiu, J. [et al.]. Prediction stability as a criterion in active learning. A: International Conference on Artificial Neural Networks. "Part of the Lecture Notes in Computer Science book series (LNCS, volume 12397)". Springer Nature, 2020, p. 157-167. DOI 10.1007/978-3-030-61616-8_13.
dc.identifier.urihttp://hdl.handle.net/2117/339882
dc.description.abstractRecent breakthroughs made by deep learning rely heavily on a large number of annotated samples. To overcome this shortcoming, active learning is a possible solution. Besides the previous active learning algorithms that only adopted information after training, we propose a new class of methods named sequential-based method based on the information during training. A specific criterion of active learning called prediction stability is proposed to prove the feasibility of sequential-based methods. We design a toy model to explain the principle of our proposed method and pointed out a possible defect of the former uncertainty-based methods. Experiments are made on CIFAR-10 and CIFAR-100, and the results indicates that prediction stability was effective and works well on fewer-labeled datasets. Prediction stability reaches the accuracy of traditional acquisition functions like entropy on CIFAR-10, and notably outperformed them on CIFAR-100.
dc.format.extent11 p.
dc.language.isoeng
dc.publisherSpringer Nature
dc.rightsAttribution-NonCommercial-NoDerivs 3.0 Spain
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/3.0/es/
dc.subjectÀrees temàtiques de la UPC::Informàtica
dc.subject.lcshMachine learning
dc.subject.otherDeep learning
dc.subject.otherActive learning
dc.subject.otherClassification
dc.subject.otherSequential-based
dc.subject.otherPrediction stability
dc.titlePrediction stability as a criterion in active learning
dc.typeConference report
dc.subject.lemacAprenentatge automàtic
dc.identifier.doi10.1007/978-3-030-61616-8_13
dc.description.peerreviewedPeer Reviewed
dc.relation.publisherversionhttps://link.springer.com/chapter/10.1007%2F978-3-030-61616-8_13
dc.rights.accessRestricted access - publisher's policy
local.identifier.drac30582065
dc.description.versionPostprint (published version)
dc.date.lift10000-01-01
local.citation.authorLiu, J.; Li, X.; Zhou, J.; Shen, J.
local.citation.contributorInternational Conference on Artificial Neural Networks
local.citation.publicationNamePart of the Lecture Notes in Computer Science book series (LNCS, volume 12397)
local.citation.startingPage157
local.citation.endingPage167


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record

Attribution-NonCommercial-NoDerivs 3.0 Spain
Except where otherwise noted, content on this work is licensed under a Creative Commons license : Attribution-NonCommercial-NoDerivs 3.0 Spain