DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | 명현 | - |
dc.contributor.author | Hong, Dasol | - |
dc.contributor.author | 홍다솔 | - |
dc.date.accessioned | 2024-07-30T19:31:39Z | - |
dc.date.available | 2024-07-30T19:31:39Z | - |
dc.date.issued | 2024 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=1097222&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/321650 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 전기및전자공학부, 2024.2,[iv, 28 p. :] | - |
dc.description.abstract | For the application of deep learning models in real-world scenarios, it is crucial to consider their robustness across a wide range of domains. Data augmentation aims to improve the robustness of a model to the domain. However, most of these data augmentation techniques have been studied in the field of image classification. When these approaches are applied to object detection, the semantic features of some objects can be damaged, which can lead to imprecise object localization and misclassification. In this paper, an object-aware data augmentation method, which is called OA-Mix, is proposed to address these problems. The method generates multi-domain data using a multi-level transformation and an object-aware mixing strategy. OA-Mix outperforms state-of-the-art methods on the benchmark to evaluate robustness in corrupted domains. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | 데이터 증강▼a객체 탐지▼a도메인 견고성▼a단일 도메인 일반화 | - |
dc.subject | Data augmentation▼aObject detection▼aDomain robustness▼aSingle-domain generalization | - |
dc.title | Data augmentation method for domain generalization in object detection | - |
dc.title.alternative | 객체 탐지에서의 도메인 일반화를 위한 데이터 증강 기법 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :전기및전자공학부, | - |
dc.contributor.alternativeauthor | Myung, Hyun | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.