• Journal of Electrical Engineering and Technology
• /
• 제13권5호
• /
• pp.2099-2106
• /
• 2018

This study presents a novel approach of discriminative feature vectors based on manifold learning using nonlinear dimension reduction (DR) technique to improve loss function, and combine with the Adversarial examples to regularize the object function for image classification. The traditional convolutional neural networks (CNN) with many new regularization approach has been successfully used for image classification tasks, and it achieved good results, hence it costs a lot of Calculated spacing and timing. Significantly, distrinct from traditional CNN, we discriminate the feature vectors for objects without empirically-tuned parameter, these Discriminative features intend to remain the lower-dimensional relationship corresponding high-dimension manifold after projecting the image feature vectors from high-dimension to lower-dimension, and we optimize the constrains of the preserving local features based on manifold, which narrow the mapped feature information from the same class and push different class away. Using Adversarial examples, improved loss function with additional regularization term intends to boost the Robustness and generalization of neural network. experimental results indicate that the approach based on discriminative feature of manifold learning is not only valid, but also more efficient in image classification tasks. Furthermore, the proposed approach achieves competitive classification performances for three benchmark datasets : MNIST, CIFAR-10, SVHN.

• International Journal of Control, Automation, and Systems
• /
• 제5권1호
• /
• pp.99-103
• /
• 2007

Translation equivalence is very important for bilingual lexicography, machine translation system and cross-lingual information retrieval. Extraction of equivalences from bilingual sentence pairs belongs to data mining problem. In this paper, discriminative learning methods are employed to filter translation equivalences. Discriminative features including translation literality, phrase alignment probability, and phrase length ratio are used to evaluate equivalences. 1000 equivalences randomly selected are filtered and then evaluated. Experimental results indicate that its precision is 87.8% and recall is 89.8% for support vector machine.

• 한국멀티미디어학회논문지
• /
• 제24권1호
• /
• pp.13-20
• /
• 2021

A Wasserstein GAN(WGAN), optimum in terms of minimizing Wasserstein distance, still suffers from inconsistent convergence or unexpected output due to inherent learning instability. It is widely known some kinds of restriction on the discriminative function should be considered to solve such problems, which implies the importance of Lipschitz continuity. Unfortunately, there are few known methods to satisfactorily maintain the Lipschitz continuity of the discriminative function. In this paper we propose techniques to stably maintain the Lipschitz continuity of the discriminative function by adding effective regularization terms to the objective function, which limit the magnitude of the gradient vectors of the discriminator to one or less. Extensive experiments are conducted to evaluate the performance of the proposed techniques, which shows the single-sided penalty improves convergence compared with the gradient penalty at the early learning process, while the proposed additional penalty increases inception scores by 0.18 after 100,000 number of learning.

• 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.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제14권3호
• /
• pp.209-215
• /
• 2014

Sequence tagging is the task of predicting frame-wise labels for a given input sequence and has important applications to diverse domains. Conventional methods such as maximum likelihood (ML) learning matches global features in empirical and model distributions, rather than local features, which directly translates into frame-wise prediction errors. Recent probabilistic sequence models such as conditional random fields (CRFs) have achieved great success in a variety of situations. In this paper, we introduce a novel discriminative CRF learning algorithm to minimize local feature mismatches. Unlike overall data fitting originating from global feature matching in ML learning, our approach reduces the total error over all frames in a sequence. We also provide an efficient gradient-based learning method via gradient forward-backward recursion, which requires the same computational complexity as ML learning. For several real-world sequence tagging problems, we empirically demonstrate that the proposed learning algorithm achieves significantly more accurate prediction performance than standard estimators.

• 대한임베디드공학회논문지
• /
• 제16권6호
• /
• pp.323-330
• /
• 2021

Visual object tracking is a challenging area of study in the field of computer vision due to many difficult problems, including a fast variation of target shape, occlusion, and arbitrary ground truth object designation. In this paper, we focus on the reinforced feature of the dynamic search area to get better performance than conventional discriminative model prediction trackers on the condition when the accuracy deteriorates since low feature discrimination. We propose a reinforced input feature method shown like the spotlight effect on the dynamic search area of the target tracking. This method can be used to improve performances for deep learning based discriminative model prediction tracker, also various types of trackers which are used to infer the center of the target based on the visual object tracking. The proposed method shows the improved tracking performance than the baseline trackers, achieving a relative gain of 38% quantitative improvement from 0.433 to 0.601 F-score at the visual object tracking evaluation.

• 한국음향학회지
• /
• 제41권3호
• /
• pp.335-341
• /
• 2022

본 논문에서는 기존 자연어 처리 분야에서 뛰어난 성능을 보이는 트랜스포머를 하이브리드 음성인식에서의 음향모델로 사용하였다. 트랜스포머 음향모델은 attention 구조를 사용하여 시계열 데이터를 처리하며 연산량이 낮으면서 높은 성능을 보인다. 본 논문은 이러한 트랜스포머 AM에 기존 DNN-HMM 모델에서 사용하는 가중 유한 상태 전이기(weighted Finite-State Transducer, wFST) 기반 학습인 시퀀스 분류 학습의 네 가지 알고리즘을 각각 적용하여 성능을 높이는 방법을 제안한다. 또한 기존 Cross Entropy(CE)를 사용한 학습방식과 비교하여 5 %의 상대적 word error rate(WER) 감소율을 보였다.

• 한국수학교육학회지시리즈E:수학교육논문집
• /
• 제37권2호
• /
• pp.199-212
• /
• 2023

본 연구의 목적은 수학교과에서 학습하는 내용이 영역과 유형의 차이에 따라 구획연습과 교차연습의 성취도 차이가 나는지 알아보고 이 결과를 통해 수학학습에서의 교차연습의 효과가 '분산-연습 가설'에 의한 것인지 혹은 '구분-대조 가설'에 의한 것인지를 확인하는 것이다. 교차연습이 구획연습보다 효과적이라는 연구가 대부분이지만 그 원인에 대해서 선행 연구들은 일관된 결과를 보이고 있지 않다. 이에 본 연구에서는 D광역시 중학교 1학년 103명을 구획연습, 교차연습, 먼-구획연습, 먼-교차연습 집단으로 무작위 배치하여 4회에 걸쳐 학습활동을 하였고 일주일의 파지간격을 둔 후 최종검사를 실시하였다. 그 결과, 동일한 영역에서의 유사한 유형에서는 교차연습의 효과가 나타났고, 서로 다른 영역의 다른 유형에서는 교차연습의 효과가 나타나지 않았다. 또한, 이 결과를 통해 교차연습의 효과는 '분산-연습 가설'보다는 '구분-대조 가설'에 의한 것임을 확인할 수 있었다. 연구결과와 연구방법에 대한 논의를 통해 후속 연구가 필요한 연구문제를 제안하였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권1호
• /
• pp.305-326
• /
• 2019

Discriminative correlation filter (DCF) based tracking algorithms have recently shown impressive performance on benchmark datasets. However, amount of recent researches are vulnerable to heavy occlusions, irregular deformations and so on. In this paper, we intend to solve these problems and handle the contradiction between accuracy and real-time in the framework of tracking-by-detection. Firstly, we propose an innovative strategy to combine the template and color-based models instead of a simple linear superposition and rely on the strengths of both to promote the accuracy. Secondly, to enhance the discriminative power of the learned template model, the spatial regularization is introduced in the learning stage to penalize the objective boundary information corresponding to features in the background. Thirdly, we utilize a discriminative multi-scale estimate method to solve the problem of scale variations. Finally, we research strategies to limit the computational complexity of our tracker. Abundant experiments demonstrate that our tracker performs superiorly against several advanced algorithms on both the OTB2013 and OTB2015 datasets while maintaining the high frame rates.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권4호
• /
• pp.2093-2108
• /
• 2017

In this paper, we describe a novel method for recognizing human actions from different views via view knowledge transfer. Our approach is characterized by two aspects: 1) We propose a unsupervised topic transfer model (TTM) to model two view-dependent vocabularies, where the original bag of visual words (BoVW) representation can be transferred into a bag of topics (BoT) representation. The higher-level BoT features, which can be shared across views, can connect action models for different views. 2) Our features make it possible to obtain a discriminative model of action under one view and categorize actions in another view. We tested our approach on the IXMAS data set, and the results are promising, given such a simple approach. In addition, we also demonstrate a supervised topic transfer model (STTM), which can combine transfer feature learning and discriminative classifier learning into one framework.