DC Field | Value | Language |
---|---|---|
dc.contributor.author | Seungjun Lee | - |
dc.date.accessioned | 2023-06-26T19:33:44Z | - |
dc.date.available | 2023-06-26T19:33:44Z | - |
dc.date.issued | 2022 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=1008363&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/309850 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 전기및전자공학부, 2022.8,[iv, 27 p. :] | - |
dc.description.abstract | We address object detection task in adverse weather conditions. Generally, adverse weather conditions degrade object detection performance. To overcome this drawback, we propose Continual Adaptation Learning (CAL). Specifically, we utilize Developmental Memory (DM) and Regularization Method (RM) to resolve catastrophic forgetting problem. DM and RM was invented for classification task. We research a optimal method to apply DM and RM to object detection task. In result, CAL-ODWC has improved performance. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | 연속 학습▼a평생학습▼a치명적 망각▼a도메인 적응학습▼a발달형 메모리▼a정규화 기법▼a악천후 기상 상황▼a객체 감지 | - |
dc.subject | Continual Learning▼aLifelong Learning▼aCatastrophic Forgetting▼aDomain Adaptation▼aDevelopmental Memory▼aRegularization Method▼aAdverse Weather Condition▼aObject Detection | - |
dc.title | CAL-ODWC: continual adaptation learning for object detection under weather changes | - |
dc.title.alternative | 악천후 기상상황 속 객체 감지를 위한 연속적 적응학습 기법 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :전기및전자공학부, | - |
dc.contributor.alternativeauthor | 이승준 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.