1. Identity statement | |
Reference Type | Conference Paper (Conference Proceedings) |
Site | sibgrapi.sid.inpe.br |
Identifier | 8JMKD3MGPEW34M/47JR2EL |
Repository | sid.inpe.br/sibgrapi/2022/09.10.02.27 |
Last Update | 2022:09.26.18.26.18 (UTC) administrator |
Metadata Repository | sid.inpe.br/sibgrapi/2022/09.10.02.27.09 |
Metadata Last Update | 2023:05.23.04.20.42 (UTC) administrator |
DOI | 10.1109/SIBGRAPI55357.2022.9991760 |
Citation Key | FontinelePeteOliv:2022:BoLeBe |
Title | No boundary left behind in semantic segmentation |
Short Title | No boundary left behind |
Format | On-line |
Year | 2022 |
Access Date | 2025, Feb. 05 |
Number of Files | 2 |
Size | 4117 KiB |
|
2. Context | |
Author | 1 Fontinele, Jefferson 2 Peters, Bernardo 3 Oliveira, Luciano |
Affiliation | 1 Universidade Federal do Maranhão 2 Ivisionlab, Universidade Federal da Bahia 3 Ivisionlab, Universidade Federal da Bahia |
e-Mail Address | lrebouca@ufba.br |
Conference Name | Conference on Graphics, Patterns and Images, 35 (SIBGRAPI) |
Conference Location | Natal, RN |
Date | 24-27 Oct. 2022 |
Book Title | Proceedings |
Tertiary Type | Full Paper |
History (UTC) | 2022-09-26 18:26:19 :: lrebouca@ufba.br -> administrator :: 2022 2023-05-23 04:20:42 :: administrator -> :: 2022 |
|
3. Content and structure | |
Is the master or a copy? | is the master |
Content Stage | completed |
Transferable | 1 |
Keywords | semantic segmentation boundary deep learning |
Abstract | This paper proposes a novel network architecture for image semantic segmentation based on attention mechanisms placed on specific points inside a convolutional neural network. Attention is explored across our network to integrate information from object boundary and a baseline semantic segmenter (inner segmentation). We call our novel network Attention-fitted Fusion of boundary and Inner Segmentation (AFIS), which combines the two streams through a set of attention gates, forming an end-to-end network. We performed an extensive evaluation of our method over four public challenging data sets (Cityscapes, CamVid, Pascal Context, and Mapillary Vistas), finding supe- rior results when compared with other twelve state-of-the-art segmenters, considering the same training conditions. |
Arrangement | urlib.net > SDLA > Fonds > SIBGRAPI 2022 > No boundary left behind |
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/47JR2EL |
zipped data URL | http://urlib.net/zip/8JMKD3MGPEW34M/47JR2EL |
Language | en |
Target File | fontinele-37.pdf |
User Group | lrebouca@ufba.br |
Visibility | shown |
|
5. Allied materials | |
Mirror Repository | sid.inpe.br/banon/2001/03.30.15.38.24 |
Next Higher Units | 8JMKD3MGPEW34M/495MHJ8 |
Citing Item List | sid.inpe.br/sibgrapi/2023/05.19.12.10 39 sid.inpe.br/sibgrapi/2022/06.10.21.49 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 documentstage edition editor electronicmailaddress group holdercode isbn issn label lineage mark nextedition notes numberofvolumes orcid organization pages parameterlist parentrepositories previousedition previouslowerunit progress project publisher publisheraddress readergroup readpermission resumeid rightsholder schedulinginformation secondarydate secondarykey secondarymark secondarytype serieseditor session sponsor subject tertiarymark type url versiontype volume |
|