Episodic training using random bias sampling무작위 편향 샘플링을 이용한 에피소딕 학습법

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 75
  • Download : 0
In recent years, few-shot classification using meta-learning has emerged as an approach to solve the problem of general deep learning whereby a model requires a large amount of data to learn a new concept. Existing studies on meta-learning use the episodic training method, which generates episodes from training datasets and optimizes the model. However, as the model is strongly associated with the given training data, it is possible to decrease its overall performance depending on the characteristics of the test dataset. In this dissertation, we propose a new episodic training method to provide robust performance for various datasets based on random bias sampling, which samples many sub-datasets from the training data. The proposed method uses the structural features of a large-scale hierarchical dataset to sample an intentionally biased dataset based on the depth information. Therefore, we make the trained model reflect sampled datasets that were derived from a hierarchy with a large depth having a high bias, and the training experience has been provided using various datasets. To evaluate whether the trained model functions suitably on different datasets for few-shot classification tasks, we conduct experiments that apply our method to the matching network and prototypical network to measure the accuracies for five datasets.
Advisors
Choi, Ho-Jinresearcher최호진researcher
Description
한국과학기술원 :전산학부,
Publisher
한국과학기술원
Issue Date
2021
Identifier
325007
Language
eng
Description

학위논문(석사) - 한국과학기술원 : 전산학부, 2021.2,[iii,25p :]

Keywords

Meta-learning▼aEpisodic training▼aFew-shot classification▼aDomain adaptation▼aDomain generalization; 메타러닝▼a에피소딕 학습법▼a퓨샷 분류▼a도메인 적응▼a도메인 일반화

URI
http://hdl.handle.net/10203/296153
Link
http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=948449&flag=dissertation
Appears in Collection
CS-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