DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Moon, Jaekyun | - |
dc.contributor.advisor | 문재균 | - |
dc.contributor.author | Seo, Jun | - |
dc.date.accessioned | 2023-06-23T19:33:46Z | - |
dc.date.available | 2023-06-23T19:33:46Z | - |
dc.date.issued | 2022 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=1007859&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/309111 | - |
dc.description | 학위논문(박사) - 한국과학기술원 : 전기및전자공학부, 2022.8,[vi, 56 p. :] | - |
dc.description.abstract | The recent advances in artificial intelligence technology have been attributed to the exponential increase in the amount of data. On the other hand, however, it is becoming more difficult to categorize or label the data for training of artificial intelligence model. In this sense, machine learning algorithms in low-supervised situation with little or no labeled data are becoming increasingly important. This thesis proposes sparse supervision machine learning algorithms using only a few labeled data or utilizing unlabeled data. In the first part of thesis, we focus on the few-shot learning method that trains the model to classify new classes with only a few labeled data. The proposed few-shot learning model has the ability to quickly adapt to new tasks through a linear projection of the feature space. In the second part, we focus on the few-shot segmentation, which aims to conduct semantic segmentation for a new class with only a small amount of data. We propose a few-shot segmentation method utilizing existing semantic segmentation model by transforming the unfamiliar novel feature into more comprehensible form based on the few labeled data. Finally in the third part, we focus on the self-supervised learning method that trains the useful representation using the unlabeled data. We propose an contrastive self-supervised learning method utilizing the nonlinear feature transformation via the self-attention technique to overcome the limitation of the existing contrastive self-supervised learning methods. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | Meta learning▼aFew-shot learning▼aSelf-supervised learning▼aRepresentation learning | - |
dc.subject | 메타학습▼a소수샷학습▼a자기지도학습▼a표상학습 | - |
dc.title | Machine learning algorithms for sparse supervision | - |
dc.title.alternative | 저지도 상황에서의 기계학습 알고리즘 연구 | - |
dc.type | Thesis(Ph.D) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :전기및전자공학부, | - |
dc.contributor.alternativeauthor | 서준 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.