Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/142828
Full metadata record
DC FieldValueLanguage
dc.contributor.authorRagusa, Edoardoen_US
dc.contributor.authorCambria, Eriken_US
dc.contributor.authorZunino, Rodolfoen_US
dc.contributor.authorGastaldo, Paoloen_US
dc.date.accessioned2020-07-03T03:38:15Z-
dc.date.available2020-07-03T03:38:15Z-
dc.date.issued2019-
dc.identifier.citationRagusa, E., Cambria, E., Zunino, R., & Gastaldo, P. (2019). A survey on deep learning in image polarity detection : balancing generalization performances and computational costs. Electronics, 8(7), 783-. doi:10.3390/electronics8070783en_US
dc.identifier.issn2079-9292en_US
dc.identifier.urihttps://hdl.handle.net/10356/142828-
dc.description.abstractDeep convolutional neural networks (CNNs) provide an effective tool to extract complex information from images. In the area of image polarity detection, CNNs are customarily utilized in combination with transfer learning techniques to tackle a major problem: The unavailability of large sets of labeled data. Thus, polarity predictors in general exploit a pre-trained CNN as the feature extractor that in turn feeds a classification unit. While the latter unit is trained from scratch, the pre-trained CNN is subject to fine-tuning. As a result, the specific CNN architecture employed as the feature extractor strongly affects the overall performance of the model. This paper analyses state-of-the-art literature on image polarity detection and identifies the most reliable CNN architectures. Moreover, the paper provides an experimental protocol that should allow assessing the role played by the baseline architecture in the polarity detection task. Performance is evaluated in terms of both generalization abilities and computational complexity. The latter attribute becomes critical as polarity predictors, in the era of social networks, might need to be updated within hours or even minutes. In this regard, the paper gives practical hints on the advantages and disadvantages of the examined architectures both in terms of generalization and computational cost.en_US
dc.language.isoenen_US
dc.relation.ispartofElectronicsen_US
dc.rights© 2019 The Authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).en_US
dc.subjectEngineering::Computer science and engineeringen_US
dc.titleA survey on deep learning in image polarity detection : balancing generalization performances and computational costsen_US
dc.typeJournal Articleen
dc.contributor.schoolSchool of Computer Science and Engineeringen_US
dc.identifier.doi10.3390/electronics8070783-
dc.description.versionPublished versionen_US
dc.identifier.scopus2-s2.0-85071026354-
dc.identifier.issue7en_US
dc.identifier.volume8en_US
dc.subject.keywordsConvolutional Neural Networksen_US
dc.subject.keywordsDeep Learningen_US
item.fulltextWith Fulltext-
item.grantfulltextopen-
Appears in Collections:SCSE Journal Articles

SCOPUSTM   
Citations 20

10
Updated on Mar 10, 2021

PublonsTM
Citations 20

5
Updated on Mar 7, 2021

Page view(s)

92
Updated on Jan 28, 2022

Download(s)

5
Updated on Jan 28, 2022

Google ScholarTM

Check

Altmetric


Plumx

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.