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
- 발행연도
- 2023.11
- 수록면
- 123 - 132 (10page)
이용수
초록· 키워드
오류제보하기
Semi-supervised learning utilizing both labeled and unlabeled data has recently made significant progress; however, while semi-supervised image classification research has been actively conducted and solved many problems, semisupervised semantic segmentation research still has some problems that need to be solved. In this work, semi-supervised semantic segmentation, which requires more annotation work than other tasks such as classification, was investigated because labels are required on a pixel-by-pixel basis. Consistency regularization based on input image perturbation, feature perturbation, and network perturbation in the semi-supervised learning approach showed significant performance improvement. In particular, consistency regularization through network perturbation showed excellent performance in semi-supervised semantic segmentation. However, important challenges remain. Due to pseudo-label bias, inaccurate pseudo-labels for unlabeled data can negatively affect training, which causes more serious problems in semi supervised segmentation tasks. This study mitigates the pseudo-label bias issue by expanding the network perturbation-based method, which has shown excellent results, through a simple ensemble strategy. In addition, this simple method shows improved prediction performance. The results of this study outperform previous state-of-the-art methods and achieve state-of-the-art semi-supervised segmentation performance. The proposed method can be practically applied to the handson data science domain that hardly obtains sufficient class-labels (e.g. medicine, manufacturing, etc.).
목차
ABSTRACT
1. Introduction
2. Related Work
3. Methods
4. Experiments
5. Conclusion
References
참고문헌 (0)
참고문헌 신청함께 읽어보면 좋을 논문
논문 유사도에 따라 DBpia 가 추천하는 논문입니다. 함께 보면 좋을 연관 논문을 확인해보세요!
-
The use of support vector machines in semi-supervised classification
CSAM(Communications for Statistical Applications and Methods)
2022 .03
-
자기지도학습을 이용한 준지도학습에 관한 연구
한국데이터정보과학회지
2023 .11
-
Binding Affinity Prediction Using Self-supervised Learning and QP-Ensemble
Quantitative Bio-Science
2023 .05
-
준지도 학습의 모수 선택에 관한 연구
한국데이터정보과학회지
2016 .08
-
일치성규칙과 목표값이 없는 데이터 증대를 이용하는 학습의 성능 향상 방법에 관한 연구
응용통계연구
2021 .04
-
준감독 학습과 공간 유사성을 이용한 비접근 지역의 작물 분류 - 북한 대홍단 지역 사례 연구 -
대한원격탐사학회지
2017 .10
-
Structures of Pseudo Ideal and Pseudo Atom in a Pseudo Q-Algebra
Kyungpook Mathematical Journal
2016 .01
-
An Ensemble Approach to Domain Adaptation in Sentiment Analysis
Journal of The Korean Data Analysis Society
2019 .01
-
광학영상에서의 해빙종류 분류 연구
대한원격탐사학회지
2018 .01
-
ON PSEUDO BH-ALGEBRAS
호남수학학술지
2015 .01
-
LABEL INCIDENCE ENERGY OF PARTIAL EDGE LABELED GRAPH
Proceedings of the Jangjeon Mathematical Society
2021 .01
-
Auto Segmentation Method for Electromagnetic Radiation Camera Myocardial Images
Journal of Magnetics
2020 .09
-
Factors associated with nutrition label use among female college students applying the theory of planned behavior
Nutrition Research and Practice
2015 .02
-
Factors associated with nutrition label use among female college students applying the theory of planned behavior
Nutrition Research and Practice
2015 .02
-
딥러닝 기반의 영상분할을 이용한 토지피복분류
대한원격탐사학회지
2019 .01
-
영상분할 결과 평가 방법의 적용성 비교 분석
대한원격탐사학회지
2021 .01
-
식품용 기구 표시 제도
포장계
2016 .01
-
COUNTING OF FLOWERS BASED ON K-MEANS CLUSTERING AND WATERSHED SEGMENTATION
JOURNAL OF THE KOREAN SOCIETY FOR INDUSTRIAL AND APPLIED MATHEMATICS
2023 .06
-
드론 항공영상을 이용한 딥러닝 기반 앙상블 토지 피복 분할알고리즘 개발
대한원격탐사학회지
2024 .02
이 논문의 저자 정보
최근 본 자료
댓글(0)
0
UCI(KEPA) : I410-151-24-02-088493283