• Journal of the Korean Data and Information Science Society
• /
• 제22권1호
• /
• pp.99-105
• /
• 2011

We propose a semi-supervised learning algorithm based on a form of regularization that incorporates similarity and dissimilarity penalty terms. Our approach uses a graph-based encoding of similarity and dissimilarity. We also present a model-selection method which employs cross-validation techniques to choose hyperparameters which affect the performance of the proposed method. Simulations using two types of dat sets demonstrate that the proposed method is promising.

• Journal of the Korean Data and Information Science Society
• /
• 제21권3호
• /
• pp.461-470
• /
• 2010

라벨 있는 자료가 분류규칙을 만들 만큼 충분하지 않거나, 라벨 없는 자료가 분류규칙을 만드는데 도움을 줄 수 있는 경우에는 라벨 있는 자료와 라벨 없는 자료를 모두 사용하는 준지도분류가 더 효과적이다. 준지도분류 중 그래프기반 다양체정칙법이 개발되어 최근에 많은 연구가 이루어지고 있다. 본 연구에서는 통계적학습에서 좋은 성능을 보이는 최소제곱 서포터벡터기계를 준지도분류에 적용시키는 방법을 제안한다. 모의실험을 통해 제안된 방법이 라벨 없는 자료를 잘 활용하는 것을 볼 수 있었다.

• 산업경영시스템학회지
• /
• 제46권4호
• /
• pp.312-320
• /
• 2023

Recently, there has been an increasing attempt to replace defect detection inspections in the manufacturing industry using deep learning techniques. However, obtaining substantial high-quality labeled data to enhance the performance of deep learning models entails economic and temporal constraints. As a solution for this problem, semi-supervised learning, using a limited amount of labeled data, has been gaining traction. This study assesses the effectiveness of semi-supervised learning in the defect detection process of manufacturing using the MixMatch algorithm. The MixMatch algorithm incorporates three dominant paradigms in the semi-supervised field: Consistency regularization, Entropy minimization, and Generic regularization. The performance of semi-supervised learning based on the MixMatch algorithm was compared with that of supervised learning using defect image data from the metal casting process. For the experiments, the ratio of labeled data was adjusted to 5%, 10%, 25%, and 50% of the total data. At a labeled data ratio of 5%, semi-supervised learning achieved a classification accuracy of 90.19%, outperforming supervised learning by approximately 22%p. At a 10% ratio, it surpassed supervised learning by around 8%p, achieving a 92.89% accuracy. These results demonstrate that semi-supervised learning can achieve significant outcomes even with a very limited amount of labeled data, suggesting its invaluable application in real-world research and industrial settings where labeled data is limited.

• 응용통계연구
• /
• 제34권2호
• /
• pp.167-175
• /
• 2021

준지도학습(semi-supervised learning)은 목표값이 있는 데이터와 없는 데이터를 모두 이용하는 학습방법이다. 준지도학습에서 최근에 많은 관심을 받는 일치성규칙(consistency regularization)과 데이터 증대를 이용한 준지도학습(unsupervised data augmentation; UDA)은 목표값이 없는 데이터를 증대하여 학습에 이용한다. 그리고 성능 향상을 위해 훈련신호강화(training signal annealing; TSA)와 신뢰기반 마스킹(confidence based masking)을 이용한다. 본 연구에서는 UDA에서 사용하는 KL-정보량(Kullback-Leibler divergence)과 TSA 대신 JS-정보량(Jensen-Shanon divergene)과 역-TSA를 사용하고 신뢰기반 마스킹을 제거하는 방법을 제안한다. 실험을 통해 제안된 방법의 성능이 더 우수함을 보였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권3호
• /
• pp.1403-1417
• /
• 2019

With the rapid growth of multimedia data, research on cross-media feature learning has significance in many applications, such as multimedia search and recommendation. Existing methods are sensitive to noise and edge information in multimedia data. In this paper, we propose a semi-supervised method for cross-media feature learning by means of $L_{2,q}$ norm to improve the performance of cross-media retrieval, which is more robust and efficient than the previous ones. In our method, noise and edge information have less effect on the results of cross-media retrieval and the dynamic patch information of multimedia data is employed to increase the accuracy of cross-media retrieval. Our method can reduce the interference of noise and edge information and achieve fast convergence. Extensive experiments on the XMedia dataset illustrate that our method has better performance than the state-of-the-art methods.

• 방송공학회논문지
• /
• 제26권1호
• /
• pp.79-87
• /
• 2021

본 논문에서는 소량의 레이블 데이터로 딥러닝 기반 분류 모델을 훈련할 때 적용되는 준 지도 학습 기법 (semi-supervised learning: SSL)에 대해서 분석한다. 기존의 준 지도 학습 기법은 크게 일관성 정규화 (consistency regularization), 엔트로피 기반 (entropybased), 의사 레이블링 (pseudo labeling)으로 구분할 수 있다. 우선, 각 준 지도 학습 기법의 알고리즘에 대해서 서술한다. 실험에서는 준 지도학습 기법을 레이블 데이터의 수를 변화시키면서 훈련 후 분류 정확도를 평가한다. 최종적으로 실험 결과를 바탕으로 기존 준 지도 학습 기법의 한계에 대해서 서술하고, 분류 성능을 향상하기 위한 연구 방향을 제시한다.

• Smart Structures and Systems
• /
• 제31권4호
• /
• pp.365-381
• /
• 2023

The existing vision-based techniques for inspection and condition assessment of civil infrastructure are mostly manual and consequently time-consuming, expensive, subjective, and risky. As a viable alternative, researchers in the past resorted to deep learning-based autonomous damage detection algorithms for expedited post-disaster reconnaissance of structures. Although a number of automatic damage detection algorithms have been proposed, the scarcity of labeled training data remains a major concern. To address this issue, this study proposed a semi-supervised learning (SSL) framework based on consistency regularization and cross-supervision. Image data from post-earthquake reconnaissance, that contains cracks, spalling, and exposed rebars are used to evaluate the proposed solution. Experiments are carried out under different data partition protocols, and it is shown that the proposed SSL method can make use of unlabeled images to enhance the segmentation performance when limited amount of ground truth labels are provided. This study also proposes DeepLab-AASPP and modified versions of U-Net++ based on channel-wise attention mechanism to better segment the components and damage areas from images of reinforced concrete buildings. The channel-wise attention mechanism can effectively improve the performance of the network by dynamically scaling the feature maps so that the networks can focus on more informative feature maps in the concatenation layer. The proposed DeepLab-AASPP achieves the best performance on component segmentation and damage state segmentation tasks with mIoU scores of 0.9850 and 0.7032, respectively. For crack, spalling, and rebar segmentation tasks, modified U-Net++ obtains the best performance with Igou scores (excluding the background pixels) of 0.5449, 0.9375, and 0.5018, respectively. The proposed architectures win the second place in IC-SHM2021 competition in all five tasks of Project 2.