지원사업
학술연구/단체지원/교육 등 연구자 활동을 지속하도록 DBpia가 지원하고 있어요.
커뮤니티
연구자들이 자신의 연구와 전문성을 널리 알리고, 새로운 협력의 기회를 만들 수 있는 네트워킹 공간이에요.
논문 기본 정보
- 자료유형
- 학술저널
- 저자정보
- 저널정보
- 한국통계학회 CSAM(Communications for Statistical Applications and Methods) CSAM(Communications for Statistical Applications and Methods) 제30권 제6호
- 발행연도
- 2023.11
- 수록면
- 589 - 603 (15page)
이용수
초록· 키워드
오류제보하기
Deep generative models target to infer the underlying true data distribution, and it leads to a huge success in generating fake-but-realistic data. Regarding such a perspective, the data attributes can be a crucial factor in the data generation process since non-existent counterfactual samples can be generated by altering certain factors. For example, we can generate new portrait images by flipping the gender attribute or altering the hair color attributes. This paper proposes counterfactual disentangled variational autoencoder generative adversarial networks (CDVAE-GAN), specialized for data attribute level counterfactual data generation. The structure of the proposed CDVAE-GAN consists of variational autoencoders and generative adversarial networks. Specifically, we adopt a Gaussian variational autoencoder to extract low-dimensional disentangled data features and auxiliary Bernoulli latent variables to model the data attributes separately. Also, we utilize a generative adversarial network to generate data with high fidelity. By enjoying the benefits of the variational autoencoder with the additional Bernoulli latent variables and the generative adversarial network, the proposed CDVAE-GAN can control the data attributes, and it enables producing counterfactual data. Our experimental result on the CelebA dataset qualitatively shows that the generated samples from CDVAE-GAN are realistic. Also, the quantitative results support that the proposed model can produce data that can deceive other machine learning classifiers with the altered data attributes.
목차
Abstract
1. Introduction
2. Preliminaries
3. Methodology
4. Experiment
5. Conclusion
References
참고문헌 (0)
참고문헌 신청함께 읽어보면 좋을 논문
논문 유사도에 따라 DBpia 가 추천하는 논문입니다. 함께 보면 좋을 연관 논문을 확인해보세요!
-
Dental Image Data Generation for Instance Segmentation using Generative Adversarial Networks
Quantitative Bio-Science
2023 .11
-
대립생성망의 성능 비교에 관한 연구
한국데이터정보과학회지
2018 .09
-
CALCULATION OF FUNCTIONS ON DISENTANGLING VIA MEASURES
호남수학학술지
2018 .01
-
Partial-convolution-implemented generative adversarial network (GAN) for global oceanic data assimilation
한국기상학회 학술대회 논문집
2022 .10
-
A review on the generative models and its performance metrics
CSAM(Communications for Statistical Applications and Methods)
2025 .03
-
Generative Adversarial Networks를 이용한 WRF 강우 예측 데이터 개선
한국기상학회 학술대회 논문집
2019 .10
-
Conditional Variational Autoencoder-based inverse design and VIT-based Bulk Modulus Prediction
한국자기학회 학술연구발표회 논문개요집
2023 .05
-
Prediction of KOSPI 200 Index Movement Using Generative Adversarial Network Based on LSTM
Quantitative Bio-Science
2023 .11
-
Magnetic State Generation using Hamiltonian Guided Variational Autoencoder with Spin Structure Stabilization
한국자기학회 학술연구발표회 논문개요집
2021 .07
-
CONVERGENCE ANALYSIS OF PARALLEL S-ITERATION PROCESS FOR A SYSTEM OF VARIATIONAL INEQUALITIES USING ALTERING POINTS
Journal of applied mathematics & informatics
2018 .01
-
심층 생성 모형을 이용한 재현 데이터 생성 방법론 리뷰 및 향후 연구 제언
한국데이터정보과학회지
2023 .09
-
제너러티브 디자인 방법론을 활용한 참여적 패션디자인의 사례 연구
복식
2017 .06
-
Generative machine learning model guided by magnetic Hamiltonian
한국자기학회 학술연구발표회 논문개요집
2020 .11
-
ON OPTIMAL SOLUTIONS OF WELL-POSED PROBLEMS AND VARIATIONAL INEQUALITIES
Nonlinear Functional Analysis and Applications
2021 .12
-
Infinitely many solutions for $(p(x),q(x))$-Laplacian-like systems
대한수학회논문집
2021 .01
-
GAN 기반 합성 자료 생성 및 전단 파괴 시점 예측 모델 개발
대한지질학회 학술대회
2022 .10
-
신용카드 거래 데이터에 대한 재현 데이터 생성 방법 비교 연구
한국데이터정보과학회지
2023 .01
-
자기부호화기를 통한 수익률곡선 분해
Journal of The Korean Data Analysis Society
2018 .01
-
SOLVABILITY OF A SYSTEM OF GENERALIZED NONLINEAR MIXED VARIATIONAL-LIKE INEQUALITIES
Nonlinear Functional Analysis and Applications
2018 .03
-
Variational Tensor Network Approach for Quantum Spin Systems
한국자기학회 학술연구발표회 논문개요집
2022 .11
이 논문의 저자 정보
최근 본 자료
댓글(0)
0