• ETRI Journal
• /
• 제33권5호
• /
• pp.712-719
• /
• 2011

In this paper, we study the problem of domain adaptation for structural support vector machines (SVMs). We consider a number of domain adaptation approaches for structural SVMs and evaluate them on named entity recognition, part-of-speech tagging, and sentiment classification problems. Finally, we show that a prior model for structural SVMs outperforms other domain adaptation approaches in most cases. Moreover, the training time for this prior model is reduced compared to other domain adaptation methods with improvements in performance.

• Journal of information and communication convergence engineering
• /
• 제21권2호
• /
• pp.139-144
• /
• 2023

Engineers prefer deep neural networks (DNNs) for solving computer vision problems. However, DNNs pose two major problems. First, neural networks require large amounts of well-labeled data for training. Second, the covariate shift problem is common in computer vision problems. Domain adaptation has been proposed to mitigate this problem. Recent work on adversarial-learning-based unsupervised domain adaptation (UDA) has explained transferability and enabled the model to learn robust features. Despite this advantage, current methods do not guarantee the distinguishability of the latent space unless they consider class-aware information of the target domain. Furthermore, source and target examples alone cannot efficiently extract domain-invariant features from the encoded spaces. To alleviate the problems of existing UDA methods, we propose the mixup regularization in adversarial discriminative domain adaptation (ADDA) method. We validated the effectiveness and generality of the proposed method by performing experiments under three adaptation scenarios: MNIST to USPS, SVHN to MNIST, and MNIST to MNIST-M.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송∙미디어공학회 2022년도 하계학술대회
• /
• pp.1282-1285
• /
• 2022

기존의 video domain adaptation은 closed set 환경에서 주로 연구되었다. 하지만 이는 source와 target의 label이 같다는 비현실적인 전제를 요구한다. 따라서 본 논문에서는 target의 label space가 source보다 넓은 open set video domain adaptation 문제를 다룬다. 우린 open set image domain adaptation에서 사용되는 방법들을 video로 확장 시켜 모델을 설계하고 UCF to HMDB, HMDB to UCF 와 같은 video dataset에서 실험하였다. 그 결과 source only 대비 UCF to HMDB에서 12%, HMDB to UCF 7.1% 향상된 결과를 얻었다.

• 방송공학회논문지
• /
• 제27권4호
• /
• pp.511-518
• /
• 2022

딥러닝 기반의 지도학습은 다양한 응용 분야에서 비약적인 발전을 이루었다. 그러나 많은 지도 학습 방법들은 학습 및 테스트 데이터가 동일한 분포에서 추출된다는 공통된 가정 하에 이루어진다. 이 제약 조건에서 벗어나는 경우, 학습 도메인에서 훈련된 딥러닝 네트워크는 도메인 간의 분포 차이로 인하여 테스트 도메인에서의 성능이 급격하게 저하될 가능성이 높다. 도메인 적응 기술은 레이블이 풍부한 학습 도메인 (소스 도메인)의 학습된 지식을 기반으로 레이블이 불충분한 테스트 도메인 (타겟 도메인) 에서 성공적인 추론을 할 수 있도록 딥러닝 네트워크를 훈련하는 전이 학습의 한 방법론이다. 특히 비지도 도메인 적응 기술은 타겟 도메인에 레이블이 전혀 없는 이미지 데이터에만 접근할 수 있는 상황을 가정하여 도메인 적응 문제를 다룬다. 본 논문에서는 이러한 비지도 학습 기반의 도메인 적응 기술들에 대해 탐구한다.

• International Journal of Internet, Broadcasting and Communication
• /
• 제12권2호
• /
• pp.127-136
• /
• 2020

This paper presents an environment for rule-based English-Korean machine translation system, which supports the translation domain adaptation and the continuous translation quality improvement. For the purposes, corpus is essential, from which necessary information for translation will be acquired. The environment consists of a corpus construction part and a translation knowledge extraction part. The corpus construction part crawls news articles from some newspaper sites. The extraction part builds the translation knowledge such as newly-created words, compound words, collocation information, distributional word representations, and so on. For the translation domain adaption, the corpus for the domain should be built and the translation knowledge should be constructed from the corpus. For the continuous improvement, corpus needs to be continuously expanded and the translation knowledge should be enhanced from the expanded corpus. The proposed web-based environment is expected to facilitate the tasks of domain adaptation and translation system improvement.

• Journal of Information Science Theory and Practice
• /
• 제1권1호
• /
• pp.10-26
• /
• 2013

Domain transfer is a widely recognized problem for machine learning algorithms because models built upon one data domain generally do not perform well in another data domain. This is especially a challenge for tasks such as opinion classification, which often has to deal with insufficient quantities of labeled data. This study investigates the feasibility of self-training in dealing with the domain transfer problem in opinion classification via leveraging labeled data in non-target data domain(s) and unlabeled data in the target-domain. Specifically, self-training is evaluated for effectiveness in sparse data situations and feasibility for domain adaptation in opinion classification. Three types of Web content are tested: edited news articles, semi-structured movie reviews, and the informal and unstructured content of the blogosphere. Findings of this study suggest that, when there are limited labeled data, self-training is a promising approach for opinion classification, although the contributions vary across data domains. Significant improvement was demonstrated for the most challenging data domain-the blogosphere-when a domain transfer-based self-training strategy was implemented.

• 대한원격탐사학회지
• /
• 제38권2호
• /
• pp.199-213
• /
• 2022

비지도 도메인 적응은 연단위 작물 분류를 위해 매년 반복적으로 양질의 훈련자료를 수집해야 하는 비실용적인 문제를 해결할 수 있다. 이 연구에서는 작물 분류를 위한 딥러닝 기반 비지도 도메인 적응 모델의 적용성을 평가하였다. 우리나라 마늘, 양파 주산지인 합천군과 창녕군을 대상으로 무인기 영상을 이용한 작물 분류 실험을 통해 deep adaptation network (DAN), deep reconstruction-classification network, domain adversarial neural network (DANN)의 3개의 비지도 도메인 적응 모델을 정량적으로 비교하였다. 비지도 도메인 적응 모델의 분류 성능을 평가하기 위해 소스 베이스라인 및 대상 베이스라인 모델로 convolutional neural networks (CNNs)을 추가로 적용하였다. 3개의 비지도 도메인 적응 모델은 소스 베이스라인 CNN보다 우수한 성능을 보였으나, 소스 도메인 영상과 대상 도메인 영상의 자료 분포 간 불일치 정도에 따라 서로 다른 분류 성능을 보였다. DAN의 분류 성능은 두 도메인 영상 간 불일치가 작을 때 다른 두 모델에 비해 분류 성능이 높은 반면에 DANN은 두 도메인 영상 간 불일치가 클 때 가장 우수한 분류 성능을 보였다. 따라서 신뢰할 수 있는 분류 결과를 생성하기 위해 두 도메인 영상의 분포가 일치하는 정도를 고려해서 최상의 비지도 도메인 적응 모델을 선택해야 한다.

• 한국군사과학기술학회지
• /
• 제24권4호
• /
• pp.382-391
• /
• 2021

Unsupervised domain adaptation often gives impressive solutions to handle domain shift of data. Most of current approaches assume that unlabeled target data to train is abundant. This assumption is not always true in practices. To tackle this issue, we propose a general solution to solve the domain gap minimization problem without any target data. Our method consists of two regularization steps. The first step is a pixel regularization by arbitrary style transfer. Recently, some methods bring style transfer algorithms to domain adaptation and domain generalization process. They use style transfer algorithms to remove texture bias in source domain data. We also use style transfer algorithms for removing texture bias, but our method depends on neither domain adaptation nor domain generalization paradigm. The second regularization step is a feature regularization by feature alignment. Adding a feature alignment loss term to the model loss, the model learns domain invariant representation more efficiently. We evaluate our regularization methods from several experiments both on small dataset and large dataset. From the experiments, we show that our model can learn domain invariant representation as much as unsupervised domain adaptation methods.

• 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%.

• ETRI Journal
• /
• 제36권3호
• /
• pp.429-438
• /
• 2014

Semantic role labeling (SRL) is a task in natural-language processing with the aim of detecting predicates in the text, choosing their correct senses, identifying their associated arguments, and predicting the semantic roles of the arguments. Developing a high-performance SRL system for a domain requires manually annotated training data of large size in the same domain. However, such SRL training data of sufficient size is available only for a few domains. Constructing SRL training data for a new domain is very expensive. Therefore, domain adaptation in SRL can be regarded as an important problem. In this paper, we show that domain adaptation for SRL systems can achieve state-of-the-art performance when based on structural learning and exploiting a prior model approach. We provide experimental results with three different target domains showing that our method is effective even if training data of small size is available for the target domains. According to experimentations, our proposed method outperforms those of other research works by about 2% to 5% in F-score.