Guiding deep neural networks via self-supervised learning for discriminative and generative modeling자기지도 학습을 통한 분별 및 생성 심층인공신경망 개선

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 68
  • Download : 0
Self-supervised learning, which learns by constructing artificial labels (a.k.a, self-supervision) from only the input signals, has recently gained considerable attention for learning semantic representations from unlabeled data. This dissertation investigates how to utilize such self-supervision for improving deep neural networks under various scenarios: supervised learning, transfer learning, and generative modeling. Specifically, we first propose a novel label augmentation technique using self-supervision for various fully-supervised settings, including few-shot and imbalanced classification. Second, we construct effective augmentation-aware self-supervision for improving the transferability of representations under various transfer learning scenarios. Last, we introduce a novel training framework of latent-variable energy-based models guided by self-supervised learning, which significantly improves the generation quality. Namely, we show self-supervised learning can improve both discriminative and generative modeling in deep learning.
Advisors
Shin, Jinwooresearcher신진우researcher
Description
한국과학기술원 :전기및전자공학부,
Publisher
한국과학기술원
Issue Date
2022
Identifier
325007
Language
eng
Description

학위논문(박사) - 한국과학기술원 : 전기및전자공학부, 2022.8,[v, 55 p. :]

Keywords

Deep learning▼aData augmentation▼aSelf-supervised learning▼aTransfer learning▼aGenerative modeling▼aEnergy-based model; 심층 학습▼a데이터 증강▼a자기지도 학습▼a전이 학습▼a생성 모델링▼a에너지 기반 모델

URI
http://hdl.handle.net/10203/309135
Link
http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=1007866&flag=dissertation
Appears in Collection
EE-Theses_Ph.D.(박사논문)
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