1. Identity statement | |
Reference Type | Conference Paper (Conference Proceedings) |
Site | sibgrapi.sid.inpe.br |
Holder Code | ibi 8JMKD3MGPEW34M/46T9EHH |
Identifier | 8JMKD3MGPEW34M/45C6UK8 |
Repository | sid.inpe.br/sibgrapi/2021/09.01.22.31 |
Last Update | 2021:09.02.22.41.31 (UTC) administrator |
Metadata Repository | sid.inpe.br/sibgrapi/2021/09.01.22.31.22 |
Metadata Last Update | 2022:06.14.00.00.19 (UTC) administrator |
DOI | 10.1109/SIBGRAPI54419.2021.00035 |
Citation Key | BlangerHiraJian:2021:ReNeBo |
Title | Reducing the need for bounding box annotations in Object Detection using Image Classification data |
Format | On-line |
Year | 2021 |
Access Date | 2024, Apr. 19 |
Number of Files | 1 |
Size | 4045 KiB |
|
2. Context | |
Author | 1 Blanger, Leonardo 2 Hirata, Nina S. T. 3 Jiang, Xiaoyi |
Affiliation | 1 University of Sao Paulo 2 University of Sao Paulo 3 University of Münster |
Editor | Paiva, Afonso Menotti, David Baranoski, Gladimir V. G. Proença, Hugo Pedro Junior, Antonio Lopes Apolinario Papa, João Paulo Pagliosa, Paulo dos Santos, Thiago Oliveira e Sá, Asla Medeiros da Silveira, Thiago Lopes Trugillo Brazil, Emilio Vital Ponti, Moacir A. Fernandes, Leandro A. F. Avila, Sandra |
e-Mail Address | leonardoblanger@gmail.com |
Conference Name | Conference on Graphics, Patterns and Images, 34 (SIBGRAPI) |
Conference Location | Gramado, RS, Brazil (virtual) |
Date | 18-22 Oct. 2021 |
Publisher | IEEE Computer Society |
Publisher City | Los Alamitos |
Book Title | Proceedings |
Tertiary Type | Full Paper |
History (UTC) | 2021-09-02 22:41:31 :: leonardoblanger@gmail.com -> administrator :: 2021 2022-03-02 00:54:15 :: administrator -> menottid@gmail.com :: 2021 2022-03-02 13:21:38 :: menottid@gmail.com -> administrator :: 2021 2022-06-14 00:00:19 :: administrator -> :: 2021 |
|
3. Content and structure | |
Is the master or a copy? | is the master |
Content Stage | completed |
Transferable | 1 |
Version Type | finaldraft |
Keywords | sample synthesis object detection pretraining deep learning |
Abstract | We address the problem of training Object Detection models using significantly less bounding box annotated images. For that, we take advantage of cheaper and more abundant image classification data. Our proposal consists in automatically generating artificial detection samples, with no need of expensive detection level supervision, using images with classification labels only. We also detail a pretraining initialization strategy for detection architectures using these artificially synthesized samples, before finetuning on real detection data, and experimentally show how this consistently leads to more data efficient models. With the proposed approach, we were able to effectively use only classification data to improve results on the harder and more supervision hungry object detection problem. We achieve results equivalent to those of the full data scenario using only a small fraction of the original detection data for Face, Bird, and Car detection. |
Arrangement 1 | urlib.net > SDLA > Fonds > SIBGRAPI 2021 > Reducing the need... |
Arrangement 2 | urlib.net > SDLA > Fonds > Full Index > Reducing the need... |
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/45C6UK8 |
zipped data URL | http://urlib.net/zip/8JMKD3MGPEW34M/45C6UK8 |
Language | en |
Target File | 29.pdf |
User Group | leonardoblanger@gmail.com |
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/45PQ3RS 8JMKD3MGPEW34M/4742MCS |
Citing Item List | sid.inpe.br/sibgrapi/2021/11.12.11.46 3 |
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 |
|