Full metadata record

DC Field Value Language
dc.contributor.authorHOWON LEE-
dc.contributor.authorChang-Su Kim-
dc.contributor.authorAhn, Sang Chul-
dc.date.accessioned2024-01-12T03:45:33Z-
dc.date.available2024-01-12T03:45:33Z-
dc.date.created2021-12-14-
dc.date.issued2021-07-01-
dc.identifier.issn--
dc.identifier.urihttps://pubs.kist.re.kr/handle/201004/77374-
dc.description.abstractFor image segmentation, both spatial information and contextual information are very important. CNN(Convolutional Neural Network) can make rich contextual information with deep layers. However,it is very difficult to preserve spatial information when we use CNN. We propose a novel method to preserve spatial information by using pixel shifted images. Using 4 pixel shifted images as inputs, the proposed method makes high-resolution feature maps. So, it has better performance for thin or small objects. It is very easy to attach to various networks because it does not need additional training. We show the performance improvement for semantic segmentation on Cityscapes dataset in the experimentation.-
dc.languageKorean-
dc.publisher대한전자공학회-
dc.subject영상분할-
dc.subject딥러닝-
dc.subjectpixel-
dc.subjectshift-
dc.titlePixel Shift를 이용한 딥러닝 기반 영상 분할의 성능 개선 방법-
dc.typeConference-
dc.description.journalClass2-
dc.identifier.bibliographicCitation2021년도 대한전자공학회 하계종합학술대회-
dc.citation.title2021년도 대한전자공학회 하계종합학술대회-
dc.citation.conferencePlaceKO-
dc.citation.conferencePlace제주도-
dc.citation.conferenceDate2021-06-30-
dc.relation.isPartOf2021년도 대한전자공학회 하계종합학술대회 논문집-
Appears in Collections:
KIST Conference Paper > 2021
Files in This Item:
There are no files associated with this item.
Export
RIS (EndNote)
XLS (Excel)
XML

qrcode

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

BROWSE