• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제13권3호
• /
• pp.186-199
• /
• 2013

We pose pattern classification as a density estimation problem where we consider mixtures of generative models under partially labeled data setups. Unlike traditional approaches that estimate density everywhere in data space, we focus on the density along the decision boundary that can yield more discriminative models with superior classification performance. We extend our earlier work on the recursive estimation method for discriminative mixture models to semi-supervised learning setups where some of the data points lack class labels. Our model exploits the mixture structure in the functional gradient framework: it searches for the base mixture component model in a greedy fashion, maximizing the conditional class likelihoods for the labeled data and at the same time minimizing the uncertainty of class label prediction for unlabeled data points. The objective can be effectively imposed as individual mixture component learning on weighted data, hence our mixture learning typically becomes highly efficient for popular base generative models like Gaussians or hidden Markov models. Moreover, apart from the expectation-maximization algorithm, the proposed recursive estimation has several advantages including the lack of need for a pre-determined mixture order and robustness to the choice of initial parameters. We demonstrate the benefits of the proposed approach on a comprehensive set of evaluations consisting of diverse time-series classification problems in semi-supervised scenarios.

• 한국멀티미디어학회논문지
• /
• 제25권10호
• /
• 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%.

• 한국음향학회지
• /
• 제40권6호
• /
• pp.578-586
• /
• 2021

종단간 음성인식기의 성능향상을 위한 변분 오토인코더(Variational AutoEncoder, VAE) 및 비교사 데이터 증강(Unsupervised Data Augmentation, UDA) 기반의 준지도 학습 방법을 제안한다. 제안된 방법에서는 먼저 원래의 음성데이터를 이용하여 VAE 기반 증강모델과 베이스라인 종단간 음성인식기를 학습한다. 그 다음, 학습된 증강모델로부터 증강된 데이터를 이용하여 베이스라인 종단간 음성인식기를 다시 학습한다. 마지막으로, 학습된 증강모델 및 종단간 음성인식기를 비교사 데이터 증강 기반의 준지도 학습 방법으로 다시 학습한다. 컴퓨터 모의실험 결과, 증강모델은 기존의 종단간 음성인식기의 단어오류율(Word Error Rate, WER)을 개선하였으며, 비교사 데이터 증강학습방법과 결합함으로써 성능을 더욱 개선하였다.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제35권5호
• /
• pp.325-334
• /
• 2008

자동 문서 범주화란 문서의 내용에 기반하여 미리 정의되어 있는 범주에 문서를 자동으로 할당하는 작업이다. 자동 문서 범주화에 관한 기존의 연구들은 지도 학습 기반으로서, 보통 수작업에 의해 범주가 할당된 대량의 학습 문서를 이용하여 범주화 작업을 학습한다. 그러나, 이러한 방법의 문제점은 대량의 학습 문서를 구축하기가 어렵다는 것이다. 즉, 학습 문서 생성을 위해 문서를 수집하는 것은 쉬우나, 수집된 문서에 범주를 할당하는 것은 매우 어렵고 시간이 많이 소요되는 작업이라는 것이다. 본 논문에서는 이러한 문제점을 해결하기 위해서, 준지도 학습 기반의 자동 문서 범주화 기법을 제안한다. 제안된 기법은 범주가 할당되지 않은 말뭉치와 각 범주의 핵심어만을 사용한다. 각 범주의 핵심어로부터 문맥간의 유사도 측정 기법을 이용한 부스트래핑(bootstrapping) 기법을 통하여 범주가 할당된 학습 문서를 자동으로 생성하고, 이를 이용하여 학습하고 문서 범주화 작업을 수행한다. 제안된 기법은 학습 문서 생성 작업과 대량의 학습 문서 없이 적은 비용으로 문서 범주화를 수행하고자 하는 영역에서 유용하게 사용될 수 있을 것이다.

• ETRI Journal
• /
• 제32권5호
• /
• 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
• /
• 제13권4호
• /
• 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
• /
• 제15권4호
• /
• 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
• /
• 제10권4호
• /
• 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)
• /
• 제14권12호
• /
• 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.

• 정보과학회 논문지
• /
• 제45권1호
• /
• pp.15-21
• /
• 2018

낮은 계수 표현(Low-Rank Representation, LRR) 기반 방법은 얼굴 클러스터링, 객체 검출 등의 여러 실제 응용에 널리 사용되고 있다. 이 방법은 그래프 기반 준지도 학습에서 그래프 구축에 사용할 경우 높은 예측 정확도를 확보할 수 있어 많이 사용된다. 그러나 LRR 문제를 해결하기 위해서는 알고리즘의 매 반복마다 데이터 수 크기의 정방행렬에 대해 특이값 분해를 수행하여야 하므로 계산 비효율적이다. 이를 해결하기 위해 속도를 향상시킨 발전된 LRR 방법을 제안한다. 이는 최근 발표된 Fast LRR(FaLRR)을 기반으로 하며, FaLRR이 속도는 빠르지만 실제로 분류 문제에서 성능이 낮은 것을 해결하기 위해 기반 최적화 목표에 추가 제약 조건을 도입하고 이를 최적화하는 방법을 제안한다. 실험을 통하여 제안 방법은 LRR보다 더 좋은 해를 빠르게 찾아냄을 확인할 수 있다. 또한, 동일한 해를 도출하는 방법을 찾아내기는 어렵지만 최소화하는 목표가 추가될 경우 더 좋은 결과를 나타내는 Fast MLRR(FaMLRR)을 제안한다.