Mitigating spurious correlation for deep learning: weakly supervised and semi-supervised approach허위 상관관계에 강인한 딥 러닝 학습 방법: 약지도 학습 및 준지도 학습 기반 방법론을 중심으로

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 83
  • Download : 0
Neural networks often learn to make predictions that overly rely on spurious correlations existing in the dataset, which causes the model to be biased. Previous work tackles this issue by using explicit labeling on the spuriously correlated attributes or presuming a particular bias type. To bypass such costly supervision on the spurious attribute, we focus on developing a weaker form of supervision. We propose a weaker form of supervision, weakly supervised, and semi-supervised approaches to mitigate spurious correlation for classification and image generation. For classification, we first utilize a cheaper yet generic form of human knowledge, which can be widely applicable to various types of bias: reliance of neural networks on spurious correlation is most prominent during the early phase of training. We then propose a semi-supervised approach based on spurious attribute estimation to bridge the performance gap between weakly supervised and fully-supervised approaches. Finally, for image generation, we leverage a biased classifier to characterize the spurious correlation in the generative model as a weaker form of supervision. We then encourage the generator to synthesize minority samples that conflict with the spurious correlation.
Advisors
Shin, Jinwooresearcher신진우researcher
Description
한국과학기술원 :전기및전자공학부,
Publisher
한국과학기술원
Issue Date
2022
Identifier
325007
Language
eng
Description

학위논문(박사) - 한국과학기술원 : 전기및전자공학부, 2022.8,[v, 49 p. :]

Keywords

허위 상관관계▼a학습 분포 외 일반화▼a딥 러닝 일반화; Spurious correlation▼aOut-of-distribution generalization▼aDeep learning generalization

URI
http://hdl.handle.net/10203/309136
Link
http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=1007869&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