• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.11
• /
• pp.457-464
• /
• 2021

The advent of the big data era has enabled the rapid development of deep learning that learns rules by itself from data. In particular, the performance of CNN algorithms has reached the level of self-adjusting the source data itself. However, the existing image processing method only deals with the image data itself, and does not sufficiently consider the heterogeneous environment in which the image is generated. Images generated in a heterogeneous environment may have the same information, but their features may be expressed differently depending on the photographing environment. This means that not only the different environmental information of each image but also the same information are represented by different features, which may degrade the performance of the image analysis model. Therefore, in this paper, we propose a method to improve the performance of the image color constancy model based on Adversarial Learning that uses image data generated in a heterogeneous environment simultaneously. Specifically, the proposed methodology operates with the interaction of the 'Domain Discriminator' that predicts the environment in which the image was taken and the 'Illumination Estimator' that predicts the lighting value. As a result of conducting an experiment on 7,022 images taken in heterogeneous environments to evaluate the performance of the proposed methodology, the proposed methodology showed superior performance in terms of Angular Error compared to the existing methods.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.11
• /
• pp.465-472
• /
• 2022

In this paper, the style synthesis network is trained to generate style-synthesized video through the style synthesis through training Stylegan and the video synthesis network for video synthesis. In order to improve the point that the gaze or expression does not transfer stably, 3D face restoration technology is applied to control important features such as the pose, gaze, and expression of the head using 3D face information. In addition, by training the discriminators for the dynamics, mouth shape, image, and gaze of the Head2head network, it is possible to create a stable style synthesis video that maintains more probabilities and consistency. Using the FaceForensic dataset and the MetFace dataset, it was confirmed that the performance was increased by converting one video into another video while maintaining the consistent movement of the target face, and generating natural data through video synthesis using 3D face information from the source video's face.

• The Journal of the Convergence on Culture Technology
• /
• v.8 no.6
• /
• pp.867-871
• /
• 2022

Amid the recent rapid trend change, the change in design has a great impact on the sales of fashion companies, so it is inevitable to be careful in choosing new designs. With the recent development of the artificial intelligence field, various machine learning is being used a lot in the fashion market to increase consumers' preferences. To contribute to increasing reliability in the development of new products by quantifying abstract concepts such as preferences, we generate new images that do not exist through three adversarial generative neural networks (GANs) and numerically compare abstract concepts of preferences using pre-trained convolution neural networks (CNNs). Deep convolutional generative adversarial networks (DCGAN), Progressive growing adversarial networks (PGGAN), and Dual Discriminator generative adversarial networks (DANs), which were trained to produce comparative, high-level, and high-level images. The degree of similarity measured was considered as a preference, and the experimental results showed that D2GAN showed a relatively high similarity compared to DCGAN and PGGAN.

• Annual Conference on Human and Language Technology
• /
• 2023.10a
• /
• pp.468-473
• /
• 2023

본 논문은 사전 학습 언어 모델의 특성인 이방성과 문맥화에 주목하여 이에 대한 분석 실험과 한국어 언어 모델만의 새로운 관점을 제안한다. 최근 진행된 영어 언어 모델 분석 연구에서 영감을 받아, 한국어 언어 모델에서도 대조학습을 통한 이방성과 문맥화의 변화를 보고하였으며, 다양한 모델에 대하여 토큰들을 문맥화 정도에 따라 분류하였다. 또한, 한국어의 언어학적 특성을 고려하여, 허위 문맥화를 완화할 수 있는 토큰을 문맥 중심어로, 문맥 중심어의 임베딩을 모방하는 토큰을 문맥 기능어로 분류하는 기준을 제안하였다. 간단한 적대적 데이터 증강 실험을 통하여 제안하는 분류 기준의 가능성을 확인하였으며, 본 논문이 향후 평가 벤치마크 및 데이터셋 제작, 나아가 한국어를 위한 강건한 학습 방법론에 기여하길 바란다.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.20 no.3
• /
• pp.171-179
• /
• 2020

Recently, studies have shown that convolution neural networks are achieving the best performance in image classification, object detection, and image generation. Vision based defect inspection which is more economical than other defect inspection, is a very important for a factory automation. Although supervised anomaly detection algorithm has far exceeded the performance of traditional machine learning based method, it is inefficient for real industrial field due to its tedious annotation work, In this paper, we propose ADGAN, a unsupervised anomaly detection architecture using the variational autoencoder and the generative adversarial network which give great results in image generation task, and demonstrate whether the proposed network architecture identifies anomalous images well on MNIST benchmark dataset as well as our own welding defect dataset.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.3
• /
• pp.11-20
• /
• 2024

Among the generative models in Artificial Intelligence (AI), especially Generative Adversarial Network (GAN) has been successful in various applications such as image processing, density estimation, and style transfer. While the GAN models including Conditional GAN (CGAN), CycleGAN, BigGAN, have been extended and improved, researchers face challenges in real-world applications in specific domains such as disaster simulation, healthcare, and urban planning due to data scarcity and unstable learning causing Image distortion. This paper proposes a new progressive learning methodology called Progressive Step Training (PST) based on the Auxiliary Classifier GAN (ACGAN) that discriminates class labels, leveraging the progressive learning approach of the Progressive Growing of GAN (PGGAN). The PST model achieves 70.82% faster stabilization, 51.3% lower standard deviation, stable convergence of loss values in the later high resolution stages, and a 94.6% faster loss reduction compared to conventional methods.

• International Area Studies Review
• /
• v.16 no.3
• /
• pp.3-25
• /
• 2012

This study is to look at the relationship of entrepreneurship(innovativeness, risk-taking), the learning competence, environmental factors(the domestic market hostility, the speed of technological change) and export performance in international new ventures(INVs). In addition, the integrated model is constructed for the purpose of analysis of the moderating effects of environmental factors. Through the existing investigation, nine hypotheses are set up. PLS(Partial Least Square) analysis method is used to sample of 115 INVs. Analysis, the two elements of entrepreneurship influenced the positive(+) in the learning competence and export performance. And the relationship of learning competence and export performance is significant. In the moderating effects, only the domestic market hostility has a significant moderating effects between the learning competence and innovativeness. The results of this research shows that innovativeness influence the learning competence playing a positive role in the performance in the domestic market is higher. This point illustrates the practical implications of the importance of innovation in learning empowerment.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2019.11a
• /
• pp.50-53
• /
• 2019

본 논문에서는 도메인 어댑테이션을 이용하여 폰트 변화에 강인한 한글 분류기를 학습하는 방법을 제안한다. 제안하는 네트워크 모델은 총 7 개로 이루어져 있으며 각각 이미지로부터 폰트에 무관한 정보를 추출하는 인코더, 추출된 정보의 유효성을 판단하기 위해 이미지 재합성에 사용되는 디코더, 재합성된 이미지의 글자 분류기, 폰트 분류기, 재합성된 글자의 정교함을 판단하는 판별기(discriminator), 그리고 인코더에서 추출된 정보에 대한 글자 분류기, 폰트 분류기이다. 본 논문에서는 적대적 생성 신경망의 학습법을 따르는 도메인 어댑테이션 기법을 이용하여 인코더의 추출 정보가 폰트 정보는 속이면서 글자 분류의 정확성은 높이도록 학습하였다. 학습 결과 인코더로부터 추출되는 정보들은 폰트에 무관한 성질을 지니면서 글자 분류에 높은 정확성을 띄었으며, 추가로 디코더에서 나오는 이미지들도 원본 폰트와 같은 이미지를 생성해 낼 수 있었다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2022.11a
• /
• pp.91-94
• /
• 2022

자율주행 자동차 개발 연구가 활발히 진행됨에 따라 객체 검출기의 성능이 중요하게 되었다. 딥러닝 기술의 발전하면서 객체 검출기의 성능도 큰 발전을 이루었다. 그에 따라 도로 위 차량 검출기의 성능도 발전하고 있으나 평상시 낮 도로상황에서 잘 동작하던 모델은 안개가 끼거나 밤 상황이 되면 제대로 동작하지 못하는 문제를 가지고 있다. 이유는 딥러닝 모델이 학습할 때 사용한 데이터셋의 정보에 따라 특정 도메인에 편향된 특성을 학습하기 때문이다. 따라서, 본 논문에서는 객체 검출 신경망에 도메인 판별기를 적용하여 이와 같은 도메인 이동 문제를 극복하는 모델을 제안한다. 모델의 성능을 Cityscapes 데이터셋과 Foggy Cityscapes 데이터셋을 사용하여 평가한 결과, 기존의 특정 도메인에서 학습한 모델보다 제안하는 모델의 검출 성능이 개선된다는 것을 확인하였다.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.12 no.6
• /
• pp.629-635
• /
• 2019

In Deep Learning models derivative is implemented by error back-propagation which enables the model to learn the error and update parameters. It can find the global (or local) optimal points of parameters even in the complex models taking advantage of a huge improvement in computing power. However, deliberately generated data points can 'fool' models and degrade the performance such as prediction accuracy. Not only these adversarial examples reduce the performance but also these examples are not easily detectable with human's eyes. In this work, we propose the method to detect adversarial datasets with random noise addition. We exploit the fact that when random noise is added, prediction accuracy of non-adversarial dataset remains almost unchanged, but that of adversarial dataset changes. We set attack methods (FGSM, Saliency Map) and noise level (0-19 with max pixel value 255) as independent variables and difference of prediction accuracy when noise was added as dependent variable in a simulation experiment. We have succeeded in extracting the threshold that separates non-adversarial and adversarial dataset. We detected the adversarial dataset using this threshold.