DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | 윤영규 | - |
dc.contributor.author | Bae, Seoungbin | - |
dc.contributor.author | 배성빈 | - |
dc.date.accessioned | 2024-07-30T19:31:24Z | - |
dc.date.available | 2024-07-30T19:31:24Z | - |
dc.date.issued | 2024 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=1096793&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/321575 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 전기및전자공학부, 2024.2,[iii, 26 p. :] | - |
dc.description.abstract | Cell segmentation in microscopy images is crucial for various biological analyses, yet obtaining labeled data for cell segmentation is challenging. Our research proposes a self-supervised learning method for cell segmentation, leveraging a neural network characterized by transformation-equivariance. The network’s ability to apply equivariant transformations to both input and output, combined with the symmetrical cells under specific transformations, enables efficient cell segmentation using a single image itself. We overcame constraints associated with the need for labeled data and the requirement of a solitary cell in images. Through various kinds of cell images, our method showed the performance performance comparable to traditional supervised cell segmentation approaches. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | 세포 분할▼a자기 지도 학습▼a변형-등변성 뉴럴 네트워크 | - |
dc.subject | Cell segmentation▼aself-supervised learning▼atransformation-equivariant neural network | - |
dc.title | Self-supervised cell segmentation in microscopy images through transformation-equivariance learning | - |
dc.title.alternative | 변형-등변성 학습을 통한 현미경 영상에서의 자기 지도 세포 분할 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :전기및전자공학부, | - |
dc.contributor.alternativeauthor | Yoon, Young-Gyu | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.