DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | 이문용 | - |
dc.contributor.author | Cho, Yesung | - |
dc.contributor.author | 조예성 | - |
dc.date.accessioned | 2024-07-30T19:30:53Z | - |
dc.date.available | 2024-07-30T19:30:53Z | - |
dc.date.issued | 2024 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=1096211&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/321426 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 데이터사이언스대학원, 2024.2,[v, 43 p. :] | - |
dc.description.abstract | Semantic segmentation, a crucial task in computer vision, classifies pixels in an image into predefined set of objects for a diverse range of applications including autonomous driving. Adverse conditions, in particular due to fog, pose significant challenges to the models trained on clean data for autonomous driving. Unsupervised Domain Adaptation (UDA) methods aimed to address these challenges have struggled with large domain gaps caused by fog-induced shifts. Additionally, fog makes it difficult for a model to distinguish boundaries between classes clearly. Toward overcoming these challenges, our study introduces a novel framework utilizing auxiliary domains — foggy source and clean target. We leverage the foggy source to adapt the model to foggy conditions smoothly while we exploit the clean target to impart knowledge about diverse data styles. Additionally, we address class boundary blurring in foggy images through inter-class contrast adaptation (ICCA). Our approach achieves state-of-the-art performance by effectively utilizing auxiliary domains and ICCA in standard settings even with a lightweight baseline. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | 도메인 적응▼a의미론적 분할▼a보조 도메인▼a클래스 간 대비 적응 | - |
dc.subject | Domain adaptation▼aSemantic segmentation▼aAuxiliary domain▼aInter-class contrast adaptation | - |
dc.title | Smooth and clear : auxiliary domain and inter-class contrast adaptation for semantic foggy scene segmentation | - |
dc.title.alternative | 부드럽고 선명하게: 의미론적 안개 장면 세분화를 위한 보조 도메인 및 클래스 간 대비 적응 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :데이터사이언스대학원, | - |
dc.contributor.alternativeauthor | Yi, Mun Yong | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.