Identity statement area
Reference TypeConference Paper (Conference Proceedings)
Last Update2020:
Metadata Last Update2020: administrator
Citation KeyRuizKrinTodt:2020:ImDaAu
TitleIDA: Improved Data Augmentation Applied to Salient Object Detection
DateNov. 7-10, 2020
Access Date2021, Jan. 19
Number of Files1
Size2655 KiB
Context area
Author1 Ruiz, Daniel Vitor
2 Krinski, Bruno Alexandre
3 Todt, Eduardo
Affiliation1 Federal Univesity of Paraná
2 Federal Univesity of Paraná
3 Federal Univesity of Paraná
EditorMusse, Soraia Raupp
Cesar Junior, Roberto Marcondes
Pelechano, Nuria
Wang, Zhangyang (Atlas)
Conference NameConference on Graphics, Patterns and Images, 33 (SIBGRAPI)
Conference LocationVirtual
Book TitleProceedings
PublisherIEEE Computer Society
Publisher CityLos Alamitos
Tertiary TypeFull Paper
History2020-09-14 16:01:02 :: -> administrator ::
2020-10-28 20:46:47 :: administrator -> :: 2020
Content and structure area
Is the master or a copy?is the master
Content Stagecompleted
Content TypeExternal Contribution
Keywordsdata-augmentation, salient-object-detection, image-segmentation, deep-learning, image-inpainting.
AbstractIn this paper, we present an Improved Data Augmentation (IDA) technique focused on Salient Object Detection (SOD). Standard data augmentation techniques proposed in the literature, such as image cropping, rotation, flipping, and resizing, only generate variations of the existing examples, providing a limited generalization. Our method combines image inpainting, affine transformations, and the linear combination of different generated background images with salient objects extracted from labeled data. Our proposed technique enables more precise control of the object's position and size while preserving background information. The background choice is based on an inter-image optimization, while object size follows a uniform random distribution within a specified interval, and the object position is intra-image optimal. We show that our method improves the segmentation quality when used for training state-of-the-art neural networks on several famous datasets of the SOD field. Combining our method with others surpasses traditional techniques such as horizontal-flip in 0.52% for F-measure and 1.19% for Precision. We also provide an evaluation in 7 different SOD datasets, with 9 distinct evaluation metrics and an average ranking of the evaluated methods.
source Directory Contentthere are no files
agreement Directory Content
agreement.html 14/09/2020 13:01 1.2 KiB 
Conditions of access and use area
data URL
zipped data URL
Target FilePID6611905.pdf
Update Permissionnot transferred
Allied materials area
Next Higher Units8JMKD3MGPEW34M/43G4L9S
Notes area
Empty Fieldsaccessionnumber archivingpolicy archivist area callnumber copyholder copyright creatorhistory descriptionlevel dissemination doi edition electronicmailaddress group holdercode isbn issn label lineage mark nextedition notes numberofvolumes orcid organization pages parameterlist parentrepositories previousedition previouslowerunit progress project readergroup readpermission resumeid rightsholder secondarydate secondarykey secondarymark secondarytype serieseditor session shorttitle sponsor subject tertiarymark type url versiontype volume
Description control area
e-Mail (login)