Publications
Detailed Information
Minimizing Expected Losses in Perturbation Models with Multidimensional Parametric Min-cuts : 다차원 Parametric Min-cut을 응용한 섭동확률모델에서의 예측손실 최적화
Cited 0 time in
Web of Science
Cited 0 time in Scopus
- Authors
- Advisor
- 정교민
- Major
- 공과대학 전기·컴퓨터공학부
- Issue Date
- 2015-08
- Publisher
- 서울대학교 대학원
- Keywords
- Parameter Learning ; Image Segmentation ; Perturbation Model ; Skeleton Method ; Expected Loss ; Monte-Carlo Sampling
- Description
- 학위논문 (석사)-- 서울대학교 대학원 : 전기·컴퓨터공학부, 2015. 8. 정교민.
- Abstract
- We consider the problem of learning perturbation-based probabilistic models
by computing and differentiating expected losses. This is a challenging computational
problem that has traditionally been tackled using Monte Carlo-based
methods. In this work, we show how a generalization of parametric min-cuts
can be used to address the same problem, achieving high accuracy of faster than
a sampling-based baseline. Utilizing our proposed Skeleton Method, we show
that we can learn the perturbation model so as to directly minimize expected
losses. Experimental results show that this approach offers promise as a new
way of training structured prediction models under complex loss functions.
- Language
- English
- Files in This Item:
Item View & Download Count
Items in S-Space are protected by copyright, with all rights reserved, unless otherwise indicated.