• 한국음향학회지
• /
• 제41권3호
• /
• pp.351-358
• /
• 2022

심층 생성 모델의 일종인 Generative Adversarial Network(GAN)과 Variational AutoEncoder(VAE)는 비병렬 학습 데이터를 사용한 음성 변환에 새로운 방법론을 제시하고 있다. 특히, Conditional Cycle-Consistent Generative Adversarial Network(CC-GAN)과 Cycle-Consistent Variational AutoEncoder(CycleVAE)는 다수 화자 사이의 음성 변환에 우수한 성능을 보이고 있다. 그러나, CC-GAN과 CycleVAE는 비교적 적은 수의 화자를 대상으로 연구가 진행되어왔다. 본 논문에서는 100 명의 한국어 화자 데이터를 사용하여 CC-GAN과 CycleVAE의 음성 변환 성능과 확장 가능성을 실험적으로 분석하였다. 실험 결과 소규모 화자의 경우 CC-GAN이 Mel-Cepstral Distortion(MCD) 기준으로 4.5 % 우수한 성능을 보이지만 대규모 화자의 경우 CycleVAE가 제한된 학습 시간 안에 12.7 % 우수한 성능을 보였다.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2017년도 추계학술발표대회
• /
• pp.807-809
• /
• 2017

Generative adversarial networks (GAN)에 대한 간략하게 설명하고, MNIST (숫자 손 글씨 데이터 셋)를 이용한 간단한 실험을 통해 GAN 구조 구조의 이해를 돕는다. 그리고 GAN이 어떻게 응용이 되고있는지 다양한 논문들을 통해 살펴본다. 본 고에서는 GAN 논문들을 크게 이미지 스타일 변경, 3D 오브젝트 추정, 손상된 이미지 복원, 언어의 시각화, 기타 등으로 분류하였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권5호
• /
• pp.1761-1777
• /
• 2021

An image with infrared features and visible details is obtained by processing infrared and visible images. In this paper, a fusion method based on Laplacian pyramid and generative adversarial network is proposed to obtain high quality fusion images, termed as Laplacian-GAN. Firstly, the base and detail layers are obtained by decomposing the source images. Secondly, we utilize the Laplacian pyramid-based method to fuse these base layers to obtain more information of the base layer. Thirdly, the detail part is fused by a generative adversarial network. In addition, generative adversarial network avoids the manual design complicated fusion rules. Finally, the fused base layer and fused detail layer are reconstructed to obtain the fused image. Experimental results demonstrate that the proposed method can obtain state-of-the-art fusion performance in both visual quality and objective assessment. In terms of visual observation, the fusion image obtained by Laplacian-GAN algorithm in this paper is clearer in detail. At the same time, in the six metrics of MI, AG, EI, MS_SSIM, Q_abf and SCD, the algorithm presented in this paper has improved by 0.62%, 7.10%, 14.53%, 12.18%, 34.33% and 12.23%, respectively, compared with the best of the other three algorithms.

• Nuclear Engineering and Technology
• /
• 제55권6호
• /
• pp.2096-2106
• /
• 2023

Rotating machinery is widely applied in important equipment of nuclear power plants (NPPs), such as pumps and valves. The research on intelligent fault diagnosis of rotating machinery is crucial to ensure the safe operation of related equipment in NPPs. However, in practical applications, data-driven fault diagnosis faces the problem of small and imbalanced samples, resulting in low model training efficiency and poor generalization performance. Therefore, a deep convolutional conditional generative adversarial network (DCCGAN) is constructed to mitigate the impact of imbalanced samples on fault diagnosis. First, a conditional generative adversarial model is designed based on convolutional neural networks to effectively augment imbalanced samples. The original sample features can be effectively extracted by the model based on conditional generative adversarial strategy and appropriate number of filters. In addition, high-quality generated samples are ensured through the visualization of model training process and samples features. Then, a deep convolutional neural network (DCNN) is designed to extract features of mixed samples and implement intelligent fault diagnosis. Finally, based on multi-fault experimental data of motor and bearing, the performance of DCCGAN model for data augmentation and intelligent fault diagnosis is verified. The proposed method effectively alleviates the problem of imbalanced samples, and shows its application value in intelligent fault diagnosis of actual NPPs.

• International Journal of Internet, Broadcasting and Communication
• /
• 제11권4호
• /
• pp.31-36
• /
• 2019

Unsupervised neural networks have not caught enough attention until Generative Adversarial Network (GAN) was proposed. By using both the generator and discriminator networks, GAN can extract the main characteristic of the original dataset and produce new data with similarlatent statistics. However, researchers understand fully that training GAN is not easy because of its unstable condition. The discriminator usually performs too good when helping the generator to learn statistics of the training datasets. Thus, the generated data is not compelling. Various research have focused on how to improve the stability and classification accuracy of GAN. However, few studies delve into how to improve the training efficiency and to save training time. In this paper, we propose a novel optimizer, named FAST-ADAM, which integrates the Lookahead to ADAM optimizer to train the generator of a semi-supervised generative adversarial network (SSGAN). We experiment to assess the feasibility and performance of our optimizer using Canadian Institute For Advanced Research - 10 (CIFAR-10) benchmark dataset. From the experiment results, we show that FAST-ADAM can help the generator to reach convergence faster than the original ADAM while maintaining comparable training accuracy results.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권7호
• /
• pp.2547-2567
• /
• 2021

It has been widely acknowledged that occlusion impairments adversely distress many face recognition algorithms' performance. Therefore, it is crucial to solving the problem of face image occlusion in face recognition. To solve the image occlusion problem in face recognition, this paper aims to automatically de-occlude the human face majority or discriminative regions to improve face recognition performance. To achieve this, we decompose the generative process into two key stages and employ a separate generative adversarial network (GAN)-based network in both stages. The first stage generates an initial coarse face image without an occlusion mask. The second stage refines the result from the first stage by forcing it closer to real face images or ground truth. To increase the performance and minimize the artifacts in the generated result, a new refine loss (e.g., reconstruction loss, perceptual loss, and adversarial loss) is used to determine all differences between the generated de-occluded face image and ground truth. Furthermore, we build occluded face images and corresponding occlusion-free face images dataset. We trained our model on this new dataset and later tested it on real-world face images. The experiment results (qualitative and quantitative) and the comparative study confirm the robustness and effectiveness of the proposed work in removing challenging occlusion masks with various structures, sizes, shapes, types, and positions.

• 한국컴퓨터정보학회:학술대회논문집
• /
• 한국컴퓨터정보학회 2020년도 제61차 동계학술대회논문집 28권1호
• /
• pp.11-14
• /
• 2020

The importance of data in the development of deep learning is very high. Data with high morphological features are usually utilized in the domains where careful lens calibrations are needed by a human to capture those data. Synthesis of high morphological data for that domain can be a great asset to improve the classification accuracy of systems in the field. Unsupervised learning can be employed for this task. Generating photo-realistic objects of interest has been massively studied after Generative Adversarial Network (GAN) was introduced. In this paper, we propose Morpho-GAN, a method that unifies several GAN techniques to generate quality data of high morphology. Our method introduces a new suitable training objective in the discriminator of GAN to synthesize images that follow the distribution of the original dataset. The results demonstrate that the proposed method can generate plausible data as good as other modern baseline models while taking a less complex during training.

• ETRI Journal
• /
• 제41권4호
• /
• pp.415-425
• /
• 2019

Generative adversarial networks (GAN) have been successfully used in many image restoration tasks, including image denoising, super-resolution, and compression artifact reduction. By fully exploiting its characteristics, state-of-the-art image restoration techniques can be used to generate images with photorealistic details. However, there are many applications that require faithful rather than visually appealing image reconstruction, such as medical imaging, surveillance, and video coding. We found that previous GAN-training methods that used a loss function in the form of a weighted sum of fidelity and adversarial loss fails to reduce fidelity loss. This results in non-negligible degradation of the objective image quality, including peak signal-to-noise ratio. Our approach is to alternate between fidelity and adversarial loss in a way that the minimization of adversarial loss does not deteriorate the fidelity. Experimental results on compression-artifact reduction and super-resolution tasks show that the proposed method can perform faithful and photorealistic image restoration.

• 디지털콘텐츠학회 논문지
• /
• 제19권3호
• /
• pp.435-443
• /
• 2018

최근 컴퓨팅 파워의 폭발적인 발전으로 컴퓨팅의 한계 라는 장벽이 사라지면서 딥러닝 이라는 이름 하에 순환 신경망(RNN), 합성곱 신경망(CNN) 등 다양한 모델들이 제안되어 컴퓨터 비젼(Computer Vision)의 수많은 난제들을 풀어나가고 있다. 2014년 발표된 대립쌍 모델(Generative Adversarial Network)은 비지도 학습에서도 컴퓨터 비젼의 문제들을 충분히 풀어나갈 수 있음을 보였고, 학습된 생성기를 활용하여 생성의 영역까지도 연구가 가능하게 하였다. GAN은 여러 가지 모델들과 결합하여 다양한 형태로 발전되고 있다. 기계학습에는 데이터 수집의 어려움이 있다. 너무 방대하면 노이즈를 제거를 통한 효과적인 데이터셋의 정제가 어렵고, 너무 작으면 작은 차이도 큰 노이즈가 되어 학습이 쉽지 않다. 본 논문에서는 GAN 모델에 영상 프레임 내의 얼굴 영역 추출을 위한 deep CNN 모델을 전처리 필터로 적용하여 두 사람의 제한된 수집데이터로 안정적으로 학습하여 다양한 표정의 합성 이미지를 만들어 낼 수 있는 방법을 제시하였다.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송∙미디어공학회 2019년도 추계학술대회
• /
• pp.122-123
• /
• 2019

본 논문에서는 GAN(Generative Adversarial Network)을 이용한 디지털 워터마크 삽입 및 추출 방법을 제안한다. 호스트 영상의 데이터 셋은 128×128 크기의 흑백 영상인 BOssBase 데이터 셋을 사용하고, 워터마크 영상은 8×8 크기의 이진 영상을 사용한다. 네트워크는 호스트 영상에 워터마크를 삽입하는 삽입기와 워터마크가 삽입된 영상에서 워터마크를 추출하는 추출기로 구성된다. 강인성을 위해 삽입기가 생성한 영상에 공격 시뮬레이션을 수행한 다음에 워터마크를 추출한다. 그 결과, PSNR은 31.47dB가 나왔고, 공격에 강인한 워터마크를 추출할 수 있다.