DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Moon, Jaekyun | - |
dc.contributor.advisor | 문재균 | - |
dc.contributor.author | Kim, Do-Yeon | - |
dc.date.accessioned | 2022-04-27T19:31:12Z | - |
dc.date.available | 2022-04-27T19:31:12Z | - |
dc.date.issued | 2021 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=948690&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/295980 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 전기및전자공학부, 2021.2,[iv, 26 p. :] | - |
dc.description.abstract | Learning novel categories while preserving previously learned knowledge is a long-standing challenge in machine learning field. The challenge gets greater when a novel task is given with only a few labeled samples for each novel category, which is known as \textit{incremental few-shot learning} problem. We propose \textit{XtarNet}, which learns to extract task-adaptive representation for facilitating incremental few-shot learning. The method utilizes a backbone network pretrained on a set of base categories while also employing additional meta modules. These additional modules are trained across episodes via meta-learning based approach. Given a new task, the novel feature extracted from the meta-trained modules is combined with the base feature obtained from the pretrained model. The process of combining these two different features provides desired task-adaptive representation, which is called TAR. The TAR contains effective information to aid classifying both novel and base categories. The base and novel classifiers quickly adapt to a given task by utilizing the TAR. Experiments on standard image datasets indicate that our method achieves state-of-the-art incremental few-shot learning performance and further ablation shows the effectiveness of the TAR. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | Machine Learning▼ameta-learning▼aincremental few-shot learning▼atask-adaptive representation▼ameta-trained modules | - |
dc.subject | 기계 학습▼a메타 학습▼a점진적 소수샷 학습▼a작업적응형 표상▼a메타 학습된 모듈 | - |
dc.title | Learning to extract task-adaptive representation for incremental few-shot learning | - |
dc.title.alternative | 점진적 소수샷 학습을 위한 작업적응형 표상 추출기법 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :전기및전자공학부, | - |
dc.contributor.alternativeauthor | 김도연 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.