1. Identity statement | |
Reference Type | Conference Paper (Conference Proceedings) |
Site | sibgrapi.sid.inpe.br |
Holder Code | ibi 8JMKD3MGPEW34M/46T9EHH |
Identifier | 8JMKD3MGPAW/3RN5TEE |
Repository | sid.inpe.br/sibgrapi/2018/08.27.16.23 |
Last Update | 2018:08.27.16.57.45 (UTC) administrator |
Metadata Repository | sid.inpe.br/sibgrapi/2018/08.27.16.23.42 |
Metadata Last Update | 2022:06.14.00.09.08 (UTC) administrator |
DOI | 10.1109/SIBGRAPI.2018.00063 |
Citation Key | CavallariRibePont:2018:DoCrFe |
Title | Unsupervised representation learning using convolutional and stacked auto-encoders: a domain and cross-domain feature space analysis |
Format | On-line |
Year | 2018 |
Access Date | 2024, May 01 |
Number of Files | 1 |
Size | 1208 KiB |
|
2. Context | |
Author | 1 Cavallari, Gabriel B. 2 Ribeiro, Leonardo S. F. 3 Ponti, Moacir A. |
Affiliation | 1 USP 2 USP 3 USP |
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 | moacir@icmc.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) | 2018-08-27 16:57:45 :: moacir@icmc.usp.br -> administrator :: 2018 2022-06-14 00:09:08 :: 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 Representation learning Feature extraction Unsupervised feature learning |
Abstract | A feature learning task involves training models that are capable of inferring good representations (transformations of the original space) from input data alone. When working with limited or unlabelled data, and also when multiple visual domains are considered, methods that rely on large annotated datasets, such as Convolutional Neural Networks (CNNs), cannot be employed. In this paper we investigate different auto-encoder (AE) architectures, which require no labels, and explore training strategies to learn representations from images. The models are evaluated considering both the reconstruction error of the images and the feature spaces in terms of their discriminative power. We study the role of dense and convolutional layers on the results, as well as the depth and capacity of the networks, since those are shown to affect both the dimensionality reduction and the capability of generalising for different visual domains. Classification results with AE features were as discriminative as pre-trained CNN features. Our findings can be used as guidelines for the design of unsupervised representation learning methods within and across domains. |
Arrangement 1 | urlib.net > SDLA > Fonds > SIBGRAPI 2018 > Unsupervised representation learning... |
Arrangement 2 | urlib.net > SDLA > Fonds > Full Index > Unsupervised representation learning... |
doc Directory Content | access |
source Directory Content | sibgrapi-2018_Analysis_of_cross_domain_unsupervised_learning.pdf | 27/08/2018 13:23 | 1.2 MiB | |
agreement Directory Content | |
|
4. Conditions of access and use | |
data URL | http://urlib.net/ibi/8JMKD3MGPAW/3RN5TEE |
zipped data URL | http://urlib.net/zip/8JMKD3MGPAW/3RN5TEE |
Language | en |
Target File | sibgrapi-2018_Analysis_of_cross_domain_unsupervised_learning.pdf |
User Group | moacir@icmc.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 |
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 |
|