Mimicking key samples for knowledge transfer of GAN키 샘플 모방을 통한 생성적 적대 신경망의 전이 학습

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 130
  • Download : 0
DC FieldValueLanguage
dc.contributor.advisorShin, Jinwoo-
dc.contributor.advisor신진우-
dc.contributor.authorPark, Jongjin-
dc.date.accessioned2021-05-11T19:33:50Z-
dc.date.available2021-05-11T19:33:50Z-
dc.date.issued2019-
dc.identifier.urihttp://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=875364&flag=dissertationen_US
dc.identifier.urihttp://hdl.handle.net/10203/283070-
dc.description학위논문(석사) - 한국과학기술원 : 전기및전자공학부, 2019.8,[iii, 16 p. :]-
dc.description.abstractTransfer learning methods are arguably the most trustworthy techniques for boosting the performance of machine learning models. However, for image generation tasks, the efficient methods for transferring the knowledge of pre-trained models have not been explored compared to image classification. In this paper, we propose a novel transfer method especially for generative adversarial networks. To transfer useful knowledge from the generator and discriminator from a teacher domain, we propose teacher mimic loss (i.e., how to effectively transfer the knowledge) and sampling method (i.e., how to select samples to transfer). We demonstrate the effectiveness of the proposed method empirically.-
dc.languageeng-
dc.publisher한국과학기술원-
dc.subjectDeep learning▼atransfer learning▼agenerative adversarial networks▼aImportance sampling-
dc.subject딥러닝▼a전이학습▼a생성적 적대 신경망▼a중요도 샘플링-
dc.titleMimicking key samples for knowledge transfer of GAN-
dc.title.alternative키 샘플 모방을 통한 생성적 적대 신경망의 전이 학습-
dc.typeThesis(Master)-
dc.identifier.CNRN325007-
dc.description.department한국과학기술원 :전기및전자공학부,-
dc.contributor.alternativeauthor박종진-
Appears in Collection
EE-Theses_Master(석사논문)
Files in This Item
There are no files associated with this item.

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0