DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Choo, Jaegul | - |
dc.contributor.advisor | 주재걸 | - |
dc.contributor.author | Yun, Joo Yeol | - |
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=1032337&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/308217 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 김재철AI대학원, 2023.2,[iii, 18 p. :] | - |
dc.description.abstract | Despite the unprecedented improvement of face recognition, existing face recognition models still show considerably low performances in determining whether a pair of child and adult images belong to the same identity.Previous approaches mainly focused on increasing the similarity between child and adult images of a given identity to overcome the discrepancy of facial appearances due to aging. However, we observe that reducing the similarity between child images of different identities is crucial for learning distinct features among children and thus improving face recognition performance in child-adult pairs. Based on this intuition, we propose a novel loss function called the Inter-Prototype loss which minimizes the similarity between child images. Unlike the previous studies, the Inter-Prototype loss does not require additional child images or training additional learnable parameters. Our extensive experiments and in-depth analyses show that our approach outperforms existing baselines in face recognition with child-adult pairs. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | Face recognition▼aLarge age gaps▼aPrototype vector | - |
dc.subject | 얼굴 인식▼a큰 나이 차이▼a프로토타입 벡터 | - |
dc.title | Improving face recognition with large age gaps by learning to distinguish children | - |
dc.title.alternative | 아이들을 구별하는 법을 배움으로써 나이 차이가 많이 나는 상황에서의 얼굴인식 모델 성능 개선 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :김재철AI대학원, | - |
dc.contributor.alternativeauthor | 윤주열 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.