Generative classifier for deep discriminative classifier : novelty detection and noisy labels = 딥 분별 분류기를 위한 생성 분류기 : 노벌티 탐지 및 노이지 레이블novelty detection and noisy labels

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 45
  • Download : 0
In recent years, deep generative models have been largely dismissed for fully-supervised classification settings as they are often substantially outperformed by deep discriminative classifiers (e.g., softmax classifiers). In contrast to this common belief, this thesis shows that it is possible to formulate a simple generative classifier that is useful in detecting abnormal samples (i.e., novelty detection) and handling training samples with (incorrect) noisy labels without much sacrifice of the original discriminative per- formance with respect to in-distribution or/and clean labeled data. We believe that our approach have a potential to apply to many other related machine learning tasks, e.g., active learning, ensemble learning, and few-shot learning.
Advisors
Shin, Jinwooresearcher신진우researcher
Description
한국과학기술원 :전기및전자공학부,
Publisher
한국과학기술원
Issue Date
2020
Identifier
325007
Language
eng
Description

학위논문(박사) - 한국과학기술원 : 전기및전자공학부, 2020.2,[vi, 47p :]

Keywords

Deep generative classifier▼anovelty detection▼anoisy labels; 딥생성분류기▼a노벌티탐지▼a노이지레이블

URI
http://hdl.handle.net/10203/284205
Link
http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=909441&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