1. Identity statement | |
Reference Type | Conference Paper (Conference Proceedings) |
Site | sibgrapi.sid.inpe.br |
Holder Code | ibi 8JMKD3MGPEW34M/46T9EHH |
Identifier | 8JMKD3MGPEW34M/438SL2H |
Repository | sid.inpe.br/sibgrapi/2020/09.14.16.01 |
Last Update | 2020:09.14.16.01.01 (UTC) administrator |
Metadata Repository | sid.inpe.br/sibgrapi/2020/09.14.16.01.01 |
Metadata Last Update | 2022:06.14.00.00.02 (UTC) administrator |
DOI | 10.1109/SIBGRAPI51738.2020.00036 |
Citation Key | RuizKrinTodt:2020:ImDaAu |
Title | IDA: Improved Data Augmentation Applied to Salient Object Detection |
Format | On-line |
Year | 2020 |
Access Date | 2024, Oct. 15 |
Number of Files | 1 |
Size | 2655 KiB |
|
2. Context | |
Author | 1 Ruiz, Daniel Vitor 2 Krinski, Bruno Alexandre 3 Todt, Eduardo |
Affiliation | 1 Federal Univesity of Paraná 2 Federal Univesity of Paraná 3 Federal Univesity of Paraná |
Editor | Musse, Soraia Raupp Cesar Junior, Roberto Marcondes Pelechano, Nuria Wang, Zhangyang (Atlas) |
e-Mail Address | dvruiz@inf.ufpr.br |
Conference Name | Conference on Graphics, Patterns and Images, 33 (SIBGRAPI) |
Conference Location | Porto de Galinhas (virtual) |
Date | 7-10 Nov. 2020 |
Publisher | IEEE Computer Society |
Publisher City | Los Alamitos |
Book Title | Proceedings |
Tertiary Type | Full Paper |
History (UTC) | 2020-09-14 16:01:02 :: dvruiz@inf.ufpr.br -> administrator :: 2022-06-14 00:00:02 :: administrator -> dvruiz@inf.ufpr.br :: 2020 |
|
3. Content and structure | |
Is the master or a copy? | is the master |
Content Stage | completed |
Transferable | 1 |
Version Type | finaldraft |
Keywords | data-augmentation salient-object-detection image-segmentation deep-learning image-inpainting |
Abstract | In 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. |
Arrangement 1 | urlib.net > SDLA > Fonds > SIBGRAPI 2020 > IDA: Improved Data... |
Arrangement 2 | urlib.net > SDLA > Fonds > Full Index > IDA: Improved Data... |
doc Directory Content | access |
source Directory Content | there are no files |
agreement Directory Content | |
|
4. Conditions of access and use | |
data URL | http://urlib.net/ibi/8JMKD3MGPEW34M/438SL2H |
zipped data URL | http://urlib.net/zip/8JMKD3MGPEW34M/438SL2H |
Language | en |
Target File | PID6611905.pdf |
User Group | dvruiz@inf.ufpr.br |
Visibility | shown |
Update Permission | not transferred |
|
5. Allied materials | |
Mirror Repository | sid.inpe.br/banon/2001/03.30.15.38.24 |
Next Higher Units | 8JMKD3MGPEW34M/43G4L9S 8JMKD3MGPEW34M/4742MCS |
Citing Item List | sid.inpe.br/sibgrapi/2020/10.28.20.46 62 sid.inpe.br/sibgrapi/2022/06.10.21.49 1 sid.inpe.br/banon/2001/03.30.15.38.24 1 |
Host Collection | sid.inpe.br/banon/2001/03.30.15.38 |
|
6. Notes | |
Empty Fields | archivingpolicy archivist area callnumber contenttype copyholder copyright creatorhistory descriptionlevel dissemination edition electronicmailaddress group isbn issn label lineage mark nextedition notes numberofvolumes orcid organization pages parameterlist parentrepositories previousedition previouslowerunit progress project readergroup readpermission resumeid rightsholder schedulinginformation secondarydate secondarykey secondarymark secondarytype serieseditor session shorttitle sponsor subject tertiarymark type url volume |
|
7. Description control | |
e-Mail (login) | dvruiz@inf.ufpr.br |
update | |
|