1. Identity statement | |
Reference Type | Conference Paper (Conference Proceedings) |
Site | sibgrapi.sid.inpe.br |
Holder Code | ibi 8JMKD3MGPEW34M/46T9EHH |
Identifier | 8JMKD3MGPEW34M/45CPUQ2 |
Repository | sid.inpe.br/sibgrapi/2021/09.05.19.30 |
Last Update | 2021:09.05.19.30.23 (UTC) administrator |
Metadata Repository | sid.inpe.br/sibgrapi/2021/09.05.19.30.23 |
Metadata Last Update | 2022:06.14.00.00.26 (UTC) administrator |
DOI | 10.1109/SIBGRAPI54419.2021.00031 |
Citation Key | SilvaPedFarPapAlm:2021:ImTrDo |
Title | Improving Transferability of Domain Adaptation Networks Through Domain Alignment Layers |
Format | On-line |
Year | 2021 |
Access Date | 2024, May 06 |
Number of Files | 1 |
Size | 1571 KiB |
|
2. Context | |
Author | 1 Silva, Lucas Fernando Alvarenga e 2 Pedronette, Daniel Carlos Guimarães 3 Faria, Fabio Augusto 4 Papa, João Paulo 5 Almeida, Jurandy |
Affiliation | 1 Universidade Federal de São Paulo 2 São Paulo State University 3 Universidade Federal de São Paulo 4 São Paulo State University 5 Universidade Federal de São Paulo |
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 | e.lucas@unifesp.br |
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) | 2021-09-05 19:30:23 :: e.lucas@unifesp.br -> administrator :: 2022-03-02 00:54:15 :: administrator -> menottid@gmail.com :: 2021 2022-03-02 13:38:00 :: menottid@gmail.com -> administrator :: 2021 2022-06-14 00:00:26 :: administrator -> :: 2021 |
|
3. Content and structure | |
Is the master or a copy? | is the master |
Content Stage | completed |
Transferable | 1 |
Version Type | finaldraft |
Keywords | deep learning unsupervised domain adaptation image recognition |
Abstract | Deep learning (DL) has been the primary approach used in various computer vision tasks due to its relevant results achieved on many tasks. However, on real-world scenarios with partially or no labeled data, DL methods are also prone to the well-known domain shift problem. Multi-source unsupervised domain adaptation (MSDA) aims at learning a predictor for an unlabeled domain by assigning weak knowledge from a bag of source models. However, most works conduct domain adaptation leveraging only the extracted features and reducing their domain shift from the perspective of loss function designs. In this paper, we argue that it is not sufficient to handle domain shift only based on domain-level features, but it is also essential to align such information on the feature space. Unlike previous works, we focus on the network design and propose to embed Multi-Source version of DomaIn Alignment Layers (MS-DIAL) at different levels of the predictor. These layers are designed to match the feature distributions between different domains and can be easily applied to various MSDA methods. To show the robustness of our approach, we conducted an extensive experimental evaluation considering two challenging scenarios: digit recognition and object classification. The experimental results indicated that our approach can improve state-of-the-art MSDA methods, yielding relative gains of up to +30.64% on their classification accuracies. |
Arrangement 1 | urlib.net > SDLA > Fonds > SIBGRAPI 2021 > Improving Transferability of... |
Arrangement 2 | urlib.net > SDLA > Fonds > Full Index > Improving Transferability of... |
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/45CPUQ2 |
zipped data URL | http://urlib.net/zip/8JMKD3MGPEW34M/45CPUQ2 |
Language | en |
Target File | sibgrapi95.pdf |
User Group | e.lucas@unifesp.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/45PQ3RS 8JMKD3MGPEW34M/4742MCS |
Citing Item List | sid.inpe.br/sibgrapi/2021/11.12.11.46 4 sid.inpe.br/sibgrapi/2022/06.10.21.49 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 |
|