DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | 김대식 | - |
dc.contributor.author | Lee, Yejin | - |
dc.contributor.author | 이예진 | - |
dc.date.accessioned | 2024-07-30T19:31:48Z | - |
dc.date.available | 2024-07-30T19:31:48Z | - |
dc.date.issued | 2024 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=1097278&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/321697 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 전기및전자공학부, 2024.2,[iii, 20 p. :] | - |
dc.description.abstract | Semantic segmentation is a branch of scene understanding that can be used to perceive urban driving scenes in applications such as self-driving cars. However, existing models are trained on clear weather images, and they suffer from performance degradation when weather, season, and brightness changes. To address this issue, unsupervised domain adaptation methods have been proposed to adapt models trained on clear weather to adverse weather without ground-truth. The previous methods either utilizes reference images captured in clear weather from the same locations as the target images to address the domain gap or employs a visual boosting module for enhancement. However, all of these methods assume that the target domain follows a single distribution. In this paper, we show that the distributions in adverse weather conditions are significantly different. Therefore, it is necessary to adapt the models separately, rather than treating them as a single domain. To this end, we propose to train two Subdomain-Specialized Teachers, one for fog,rain and snow and another for night respectively. The knowledge of the two different subdomains is distilled to the student in an online manner with symmetric cross-entropy. This allows the student to have complementary knowledge from each weather domain. Our approach demonstrates the effectiveness of subdomain-specific methods by significantly reducing the performance gap between fog, rain, and snow conditions and night conditions. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | 도메인 적응▼a의미론적 장면 분할▼a지식 증류▼a악천후 조건▼a하위 도메인 세분화 | - |
dc.subject | Domain adaptation▼aSemantic segmentation▼aKnowledge distillation▼aAdverce weather condition▼aSubdomain-specific | - |
dc.title | (A) subdomain-specific knowledge distillation for unsupervised domain adaptation in adverse weather conditions | - |
dc.title.alternative | 악천후 조건의 비지도 도메인 적응을 위한 하위 도메인 세분화 지식증류 기법 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :전기및전자공학부, | - |
dc.contributor.alternativeauthor | Kim, Dae-Shik | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.