DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Choo, Jaegul | - |
dc.contributor.advisor | 주재걸 | - |
dc.contributor.author | Cho, Youngin | - |
dc.date.accessioned | 2023-06-22T19:31:24Z | - |
dc.date.available | 2023-06-22T19:31:24Z | - |
dc.date.issued | 2023 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=1032330&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/308216 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 김재철AI대학원, 2023.2,[v, 34 p. :] | - |
dc.description.abstract | Conditional generative adversarial networks (cGANs) have shown superior results in class-conditional generation tasks. To simultaneously control multiple conditions, cGANs require multi-label training datasets, where multiple labels can be assigned to each data instance. Nevertheless, the tremendous annotation cost limits the accessibility of multi-label datasets in real-world scenarios. Therefore, in this study we explore the practical setting called the single positive setting, where each data instance is annotated by only one positive label with no explicit negative labels. To generate multi-label data in the single positive setting, we propose a novel sampling approach called single-to-multi-label (S2M) sampling, based on the Markov chain Monte Carlo method. As a widely applicable “add-on” method, our proposed S2M sampling method enables existing unconditional and conditional GANs to draw high-quality multi-label data with a minimal annotation cost. Extensive experiments on real image datasets verify the effectiveness and correctness of our method, even when compared to a model trained with fully annotated datasets. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | Conditional generation▼aGenerative adversarial networks▼aMarkov chain Monte Carlo▼aMulti-label data▼aSingle positive label | - |
dc.subject | 조건부 생성▼a적대적 생성 신경망▼a마르코프 체인 몬테 카를로▼a다중 레이블 데이터▼a단일 양성 레이블 | - |
dc.title | Mining multi-label samples from single positive labels | - |
dc.title.alternative | 단일 양성 레이블을 이용한 다중 레이블 샘플 생성 방법 연구 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :김재철AI대학원, | - |
dc.contributor.alternativeauthor | 조영인 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.