1. Identity statement | |
Reference Type | Conference Paper (Conference Proceedings) |
Site | sibgrapi.sid.inpe.br |
Holder Code | ibi 8JMKD3MGPEW34M/46T9EHH |
Identifier | 8JMKD3MGPAW/3RRA45S |
Repository | sid.inpe.br/sibgrapi/2018/09.16.01.52 |
Last Update | 2018:09.16.01.52.35 (UTC) administrator |
Metadata Repository | sid.inpe.br/sibgrapi/2018/09.16.01.52.35 |
Metadata Last Update | 2022:06.14.00.09.29 (UTC) administrator |
DOI | 10.1109/SIBGRAPI.2018.00055 |
Citation Key | NazareCostMellPont:2018:EmAnUs |
Title | Color quantization in transfer learning and noisy scenarios: an empirical analysis using convolutional networks |
Format | On-line |
Year | 2018 |
Access Date | 2024, May 01 |
Number of Files | 1 |
Size | 395 KiB |
|
2. Context | |
Author | 1 Nazare, Tiago S. 2 Costa, Gabriel B. Paranhos da 3 Mello, Rodrigo F. de 4 Ponti, Moacir A. |
Affiliation | 1 University of São Paulo 2 University of São Paulo 3 University of São Paulo 4 University of São Paulo |
Editor | Ross, Arun Gastal, Eduardo S. L. Jorge, Joaquim A. Queiroz, Ricardo L. de Minetto, Rodrigo Sarkar, Sudeep Papa, João Paulo Oliveira, Manuel M. Arbeláez, Pablo Mery, Domingo Oliveira, Maria Cristina Ferreira de Spina, Thiago Vallin Mendes, Caroline Mazetto Costa, Henrique Sérgio Gutierrez Mejail, Marta Estela Geus, Klaus de Scheer, Sergio |
e-Mail Address | tiagosn@usp.br |
Conference Name | Conference on Graphics, Patterns and Images, 31 (SIBGRAPI) |
Conference Location | Foz do Iguaçu, PR, Brazil |
Date | 29 Oct.-1 Nov. 2018 |
Publisher | IEEE Computer Society |
Publisher City | Los Alamitos |
Book Title | Proceedings |
Tertiary Type | Full Paper |
History (UTC) | 2018-09-16 01:52:35 :: tiagosn@usp.br -> administrator :: 2022-06-14 00:09:29 :: administrator -> :: 2018 |
|
3. Content and structure | |
Is the master or a copy? | is the master |
Content Stage | completed |
Transferable | 1 |
Version Type | finaldraft |
Keywords | Deep learning transfer learning convolutional neural networks computer vision |
Abstract | Transfer learning is seen as one of the most promising areas of machine learning. Lately, features from pre-trained models have been used to achieve state-of-the-art results in several machine vision problems. Those models are usually employed when the problem of interest does not have enough supervised examples to support the network training from scratch. Most applications use networks pre-trained on noise-free RGB image datasets, what is observed even when the target domain counts on grayscale images or when data is degraded by noise. In this paper, we evaluate the use of Convolutional Neural Networks (CNNs) on such transfer learning scenarios and the impact of using RGB trained networks on grayscale image tasks. Our results confirm that the use of networks trained using colored images on grayscale tasks hinders the overall performance when compared to a similar network trained on a quantized version of the original dataset. Results also show that higher quantization levels (resulting in less colors) increase the robustness of CNN features in the presence of noise. |
Arrangement 1 | urlib.net > SDLA > Fonds > SIBGRAPI 2018 > Color quantization in... |
Arrangement 2 | urlib.net > SDLA > Fonds > Full Index > Color quantization in... |
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/8JMKD3MGPAW/3RRA45S |
zipped data URL | http://urlib.net/zip/8JMKD3MGPAW/3RRA45S |
Language | en |
Target File | SIB_2018.pdf |
User Group | tiagosn@usp.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 | 8JMKD3MGPAW/3RPADUS 8JMKD3MGPEW34M/4742MCS |
Citing Item List | sid.inpe.br/sibgrapi/2018/09.03.20.37 7 sid.inpe.br/sibgrapi/2022/06.10.21.49 2 |
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 |
|