• Journal of Korea Multimedia Society
• /
• v.25 no.10
• /
• pp.1375-1385
• /
• 2022

In this paper, we propose a semi-supervised domain adaptation solution to deal with practical face recognition (FR) scenarios where a single face image for each target identity (to be recognized) is only available in the training phase. Main goal of the proposed method is to reduce the discrepancy between the target and the source domain face images, which ultimately improves FR performances. The proposed method is based on the Domain Adatation network (DAN) using an MMD loss function to reduce the discrepancy between domains. In order to train more effectively, we develop a novel loss function learning strategy in which MMD loss and cross-entropy loss functions are adopted by using different weights according to the progress of each epoch during the learning. The proposed weight adoptation focuses on the training of the source domain in the initial learning phase to learn facial feature information such as eyes, nose, and mouth. After the initial learning is completed, the resulting feature information is used to training a deep network using the target domain images. To evaluate the effectiveness of the proposed method, FR performances were evaluated with pretrained model trained only with CASIA-webface (source images) and fine-tuned model trained only with FERET's gallery (target images) under the same FR scenarios. The experimental results showed that the proposed semi-supervised domain adaptation can be improved by 24.78% compared to the pre-trained model and 28.42% compared to the fine-tuned model. In addition, the proposed method outperformed other state-of-the-arts domain adaptation approaches by 9.41%.

• The Journal of the Acoustical Society of Korea
• /
• v.40 no.6
• /
• pp.578-586
• /
• 2021

We propose a semi-supervised learning method based on Variational AutoEncoder (VAE) and Unsupervised Data Augmentation (UDA) to improve the performance of an end-to-end speech recognizer. In the proposed method, first, the VAE-based augmentation model and the baseline end-to-end speech recognizer are trained using the original speech data. Then, the baseline end-to-end speech recognizer is trained again using data augmented from the learned augmentation model. Finally, the learned augmentation model and end-to-end speech recognizer are re-learned using the UDA-based semi-supervised learning method. As a result of the computer simulation, the augmentation model is shown to improve the Word Error Rate (WER) of the baseline end-to-end speech recognizer, and further improve its performance by combining it with the UDA-based learning method.

• Journal of KIISE:Software and Applications
• /
• v.35 no.5
• /
• pp.325-334
• /
• 2008

The goal of text categorization is to classify documents into a certain number of pre-defined categories. The previous studies in this area have used a large number of labeled training documents for supervised learning. One problem is that it is difficult to create the labeled training documents. While it is easy to collect the unlabeled documents, it is not so easy to manually categorize them for creating training documents. In this paper, we propose a new text categorization method based on semi-supervised learning. The proposed method uses only unlabeled documents and keywords of each category, and it automatically constructs training data from them. Then a text classifier learns with them and classifies text documents. The proposed method shows a similar degree of performance, compared with the traditional supervised teaming methods. Therefore, this method can be used in the areas where low-cost text categorization is needed. It can also be used for creating labeled training documents.

• ETRI Journal
• /
• v.32 no.5
• /
• pp.766-773
• /
• 2010

Support vector machine (SVM) active learning plays a key role in the interactive content-based image retrieval (CBIR) community. However, the regular SVM active learning is challenged by what we call "the small example problem" and "the asymmetric distribution problem." This paper attempts to integrate the merits of semi-supervised learning, ensemble learning, and active learning into the interactive CBIR. Concretely, unlabeled images are exploited to facilitate boosting by helping augment the diversity among base SVM classifiers, and then the learned ensemble model is used to identify the most informative images for active learning. In particular, a bias-weighting mechanism is developed to guide the ensemble model to pay more attention on positive images than negative images. Experiments on 5000 Corel images show that the proposed method yields better retrieval performance by an amount of 0.16 in mean average precision compared to regular SVM active learning, which is more effective than some existing improved variants of SVM active learning.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.13 no.4
• /
• pp.254-268
• /
• 2013

For real-world clustering tasks, the input data is typically not easily separable due to the highly complex data structure or when clusters vary in size, density and shape. Kernel-based clustering has proven to be an effective approach to partition such data. In this paper, we provide an overview of several fuzzy kernel clustering algorithms. We focus on methods that optimize an fuzzy C-mean-type objective function. We highlight the advantages and disadvantages of each method. In addition to the completely unsupervised algorithms, we also provide an overview of some semi-supervised fuzzy kernel clustering algorithms. These algorithms use partial supervision information to guide the optimization process and avoid local minima. We also provide an overview of the different approaches that have been used to extend kernel clustering to handle very large data sets.

• Journal of Information Processing Systems
• /
• v.15 no.4
• /
• pp.986-1016
• /
• 2019

Mobile user interface pattern (MUIP) is a kind of structured representation of interaction design knowledge. Several studies have suggested that MUIPs are a proven solution for recurring mobile interface design problems. To facilitate MUIP selection, an effective clustering method is required to discover hidden knowledge of pattern data set. In this paper, we employ the semi-supervised kernel fuzzy c-means clustering (SSKFCM) method to cluster MUIP data. In order to improve the performance of clustering, clustering parameters are optimized by utilizing the global optimization capability of particle swarm optimization (PSO) algorithm. Since the PSO algorithm is easily trapped in local optima, a novel PSO algorithm is presented in this paper. It combines an improved intuitionistic fuzzy entropy measure and a new population search strategy to enhance the population search capability and accelerate the convergence speed. Experimental results show the effectiveness and superiority of the proposed clustering method.

• Journal of Positioning, Navigation, and Timing
• /
• v.10 no.4
• /
• pp.297-305
• /
• 2021

Monocular depth estimation helps the robot to understand the surrounding environments in 3D. Especially, deep-learning-based monocular depth estimation has been widely researched, because it may overcome the scale ambiguity problem, which is a main issue in classical methods. Those learning based methods can be mainly divided into three parts: supervised learning, unsupervised learning, and semi-supervised learning. Supervised learning trains the network from dense ground-truth depth information, unsupervised one trains it from images sequences and semi-supervised one trains it from stereo images and sparse ground-truth depth. We describe the basics of each method, and then explain the recent research efforts to enhance the depth estimation performance.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.12
• /
• pp.4776-4794
• /
• 2020

We propose a rapid adaptive learning framework for streaming object detection, called EER-ASSL. The method combines the expected error reduction (EER) dependent rollback learning and the active semi-supervised learning (ASSL) for a rapid adaptive CNN detector. Most CNN object detectors are built on the assumption of static data distribution. However, images are often noisy and biased, and the data distribution is imbalanced in a real world environment. The proposed method consists of collaborative sampling and EER-ASSL. The EER-ASSL utilizes the active learning (AL) and rollback based semi-supervised learning (SSL). The AL allows us to select more informative and representative samples measuring uncertainty and diversity. The SSL divides the selected streaming image samples into the bins and each bin repeatedly transfers the discriminative knowledge of the EER and CNN models to the next bin until convergence and incorporation with the EER rollback learning algorithm is achieved. The EER models provide a rapid short-term myopic adaptation and the CNN models an incremental long-term performance improvement. EER-ASSL can overcome noisy and biased labels in varying data distribution. Extensive experiments shows that EER-ASSL obtained 70.9 mAP compared to state-of-the-art technology such as Faster RCNN, SSD300, and YOLOv2.

• Journal of KIISE
• /
• v.45 no.1
• /
• pp.15-21
• /
• 2018

Low-Rank Representation (LRR) based methods are widely used in many practical applications, such as face clustering and object detection, because they can guarantee high prediction accuracy when used to constructing graphs in graph - based semi-supervised learning. However, in order to solve the LRR problem, it is necessary to perform singular value decomposition on the square matrix of the number of data points for each iteration of the algorithm; hence the calculation is inefficient. To solve this problem, we propose an improved and faster LRR method based on the recently published Fast LRR (FaLRR) and suggests ways to introduce and optimize additional constraints on the underlying optimization goals in order to address the fact that the FaLRR is fast but actually poor in classification problems. Our experiments confirm that the proposed method finds a better solution than LRR does. We also propose Fast MLRR (FaMLRR), which shows better results when the goal of minimizing is added.

• Journal of Digital Convergence
• /
• v.20 no.4
• /
• pp.185-192
• /
• 2022

This study investigates the effect of the semi-supervised learning(SSL) method on predicting default risk of peer-to-peer(P2P) loans. Despite its proven performance, the supervised learning(SL) method requires labeled data, which may require a lot of effort and resources to collect. With the rapid growth of P2P platforms, the number of loans issued annually that have no clear final resolution is continuously increasing leading to abundance in unlabeled data. The research data of P2P loans used in this study were collected on the LendingClub platform. This is why an SSL model is needed to predict the default risk by using not only information from labeled loans(fully paid or defaulted) but also information from unlabeled loans. The results showed that in terms of default risk prediction and despite the use of a small number of labeled data, the SSL method achieved a much better default risk prediction performance than the SL method trained using a much larger set of labeled data.