DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Kim, Changick | - |
dc.contributor.advisor | 김창익 | - |
dc.contributor.author | Kim, Seunghyeon | - |
dc.date.accessioned | 2021-05-11T19:33:14Z | - |
dc.date.available | 2021-05-11T19:33:14Z | - |
dc.date.issued | 2019 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=875328&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/283034 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 전기및전자공학부, 2019.8,[v, 39 p. :] | - |
dc.description.abstract | Deep learning-based object detectors have shown remarkable improvements. However, supervised learning-based methods perform poorly when the train data and the test data have different distributions. To overcome this problem, domain adaptation transfers knowledge from the label-sufficient domain (source domain) to the label-scarce domain (target domain). Self-training is one of the powerful ways to achieve domain adaptation since it helps class-wise domain adaptation. Unfortunately, a naive approach that utilizes pseudo-labels as ground-truth seriously degenerates the performance due to incorrect pseudo-labels. In this paper, we introduce a weak self-training (WST) method and adversarial background score regularization (BSR) for domain adaptive one-stage object detection. WST diminishes the adverse effects of inaccurate pseudo-labels to stabilize the learning procedure. BSR helps the network extract discriminative features for target backgrounds to reduce the domain shift. Two components are complementary to each other as BSR enhances discrimination between foregrounds and backgrounds, whereas WST strengthen class-wise discrimination. Experimental results show that our approach effectively improves the performance of the one-stage object detection in unsupervised domain adaptation setting. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | deep learning▼aobject detection▼adomain adaptation▼aadversarial learning▼aself-training | - |
dc.subject | 딥러닝▼a객체 검출▼a도메인 적응▼a경쟁적 학습▼a자가 학습법 | - |
dc.title | Self-training and adversarial background regularization for domain adaptive one-stage object detection | - |
dc.title.alternative | 단일 과정 객체 검출기의 도메인 적응을 위한 자가 학습법과 경쟁적 배경 정규화 기법 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :전기및전자공학부, | - |
dc.contributor.alternativeauthor | 김승현 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.