scholarly journals Real Sample Consistency Regularization for GANs

Entropy ◽  
2021 ◽  
Vol 23 (9) ◽  
pp. 1231
Author(s):  
Xiangde Zhang ◽  
Jian Zhang
Keyword(s):  
Fundamental Problem ◽  
Average Distance ◽  
Synthetic Data ◽  
Real Sample ◽  
Generative Adversarial Networks ◽  
Training Process ◽  
Real Samples ◽  
Theoretical Loss ◽  
Adversarial Networks

Mode collapse has always been a fundamental problem in generative adversarial networks. The recently proposed Zero Gradient Penalty (0GP) regularization can alleviate the mode collapse, but it will exacerbate a discriminator’s misjudgment problem, that is the discriminator judges that some generated samples are more real than real samples. In actual training, the discriminator will direct the generated samples to point to samples with higher discriminator outputs. The serious misjudgment problem of the discriminator will cause the generator to generate unnatural images and reduce the quality of the generation. This paper proposes Real Sample Consistency (RSC) regularization. In the training process, we randomly divided the samples into two parts and minimized the loss of the discriminator’s outputs corresponding to these two parts, forcing the discriminator to output the same value for all real samples. We analyzed the effectiveness of our method. The experimental results showed that our method can alleviate the discriminator’s misjudgment and perform better with a more stable training process than 0GP regularization. Our real sample consistency regularization improved the FID score for the conditional generation of Fake-As-Real GAN (FARGAN) from 14.28 to 9.8 on CIFAR-10. Our RSC regularization improved the FID score from 23.42 to 17.14 on CIFAR-100 and from 53.79 to 46.92 on ImageNet2012. Our RSC regularization improved the average distance between the generated and real samples from 0.028 to 0.025 on synthetic data. The loss of the generator and discriminator in standard GAN with our regularization was close to the theoretical loss and kept stable during the training process.

scholarly journals CPGAN :  An Efficient Architecture Designing for Text-to-Image Generative Adversarial Networks Based on Canonical Polyadic Decomposition

2021 ◽  
Vol 2021 ◽  
pp. 1-9
Author(s):  
Ruixin Ma ◽  
Junying Lou
Keyword(s):  
Mobile Applications ◽  
Image Synthesis ◽  
Generative Adversarial Networks ◽  
Training Process ◽  
Adversarial Networks ◽  
Canonical Polyadic Decomposition ◽  
The Stability ◽  
Meaningful Text ◽  
General Method

Text-to-image synthesis is an important and challenging application of computer vision. Many interesting and meaningful text-to-image synthesis models have been put forward. However, most of the works pay attention to the quality of synthesis images, but rarely consider the size of these models. Large models contain many parameters and high delay, which makes it difficult to be deployed on mobile applications. To solve this problem, we propose an efficient architecture CPGAN for text-to-image generative adversarial networks (GAN) based on canonical polyadic decomposition (CPD). It is a general method to design the lightweight architecture of text-to-image GAN. To improve the stability of CPGAN, we introduce conditioning augmentation and the idea of autoencoder during the training process. Experimental results prove that our architecture CPGAN can maintain the quality of generated images and reduce at least 20% parameters and flops.

scholarly journals Improving GAN with Neighbors Embedding and Gradient Matching

2019 ◽  
Vol 33 ◽  
pp. 5191-5198
Author(s):  
Ngoc-Trung Tran ◽  
Tuan-Anh Bui ◽  
Ngai-Man Cheung
Keyword(s):  
Generative Adversarial Networks ◽  
New Techniques ◽  
Real Samples ◽  
The Real ◽  
Local Structures ◽  
Adversarial Networks ◽  
The Difference ◽  
A New Technique ◽  
Discriminator Function

We propose two new techniques for training Generative Adversarial Networks (GANs) in the unsupervised setting. Our objectives are to alleviate mode collapse in GAN and improve the quality of the generated samples. First, we propose neighbor embedding, a manifold learning-based regularization to explicitly retain local structures of latent samples in the generated samples. This prevents generator from producing nearly identical data samples from different latent samples, and reduces mode collapse. We propose an inverse t-SNE regularizer to achieve this. Second, we propose a new technique, gradient matching, to align the distributions of the generated samples and the real samples. As it is challenging to work with high-dimensional sample distributions, we propose to align these distributions through the scalar discriminator scores. We constrain the difference between the discriminator scores of the real samples and generated ones. We further constrain the difference between the gradients of these discriminator scores. We derive these constraints from Taylor approximations of the discriminator function. We perform experiments to demonstrate that our proposed techniques are computationally simple and easy to be incorporated in existing systems. When Gradient matching and Neighbour embedding are applied together, our GN-GAN achieves outstanding results on 1D/2D synthetic, CIFAR-10 and STL-10 datasets, e.g. FID score of 30.80 for the STL-10 dataset. Our code is available at: https://github.com/tntrung/gan

scholarly journals Seismic Data Augmentation Based on Conditional Generative Adversarial Networks

Sensors ◽  
2020 ◽  
Vol 20 (23) ◽  
pp. 6850
Author(s):  
Yuanming Li ◽  
Bonhwa Ku ◽  
Shou Zhang ◽  
Jae-Kwang Ahn ◽  
Hanseok Ko
Keyword(s):  
Deep Learning ◽  
Data Augmentation ◽  
Synthetic Data ◽  
Generative Adversarial Networks ◽  
High Quality ◽  
Seismic Waveforms ◽  
Adversarial Networks ◽  
Seismic Waveform ◽  
Proposed Model

Realistic synthetic data can be useful for data augmentation when training deep learning models to improve seismological detection and classification performance. In recent years, various deep learning techniques have been successfully applied in modern seismology. Due to the performance of deep learning depends on a sufficient volume of data, the data augmentation technique as a data-space solution is widely utilized. In this paper, we propose a Generative Adversarial Networks (GANs) based model that uses conditional knowledge to generate high-quality seismic waveforms. Unlike the existing method of generating samples directly from noise, the proposed method generates synthetic samples based on the statistical characteristics of real seismic waveforms in embedding space. Moreover, a content loss is added to relate high-level features extracted by a pre-trained model to the objective function to enhance the quality of the synthetic data. The classification accuracy is increased from 96.84% to 97.92% after mixing a certain amount of synthetic seismic waveforms, and results of the quality of seismic characteristics derived from the representative experiment show that the proposed model provides an effective structure for generating high-quality synthetic seismic waveforms. Thus, the proposed model is experimentally validated as a promising approach to realistic high-quality seismic waveform data augmentation.

Intrusion detection of railway clearance from infrared images using generative adversarial networks

2020 ◽  
pp. 1-13
Author(s):  
Yundong Li ◽  
Yi Liu ◽  
Han Dong ◽  
Wei Hu ◽  
Chen Lin
Keyword(s):  
Intrusion Detection ◽  
Synthetic Data ◽  
Generative Adversarial Networks ◽  
Generation Model ◽  
Single Shot ◽  
Data Generation ◽  
Infrared Images ◽  
Adversarial Networks ◽  
Training Samples ◽  
Rgb Images

The intrusion detection of railway clearance is crucial for avoiding railway accidents caused by the invasion of abnormal objects, such as pedestrians, falling rocks, and animals. However, detecting intrusions using deep learning methods from infrared images captured at night remains a challenging task because of the lack of sufficient training samples. To address this issue, a transfer strategy that migrates daytime RGB images to the nighttime style of infrared images is proposed in this study. The proposed method consists of two stages. In the first stage, a data generation model is trained on the basis of generative adversarial networks using RGB images and a small number of infrared images, and then, synthetic samples are generated using a well-trained model. In the second stage, a single shot multibox detector (SSD) model is trained using synthetic data and utilized to detect abnormal objects from infrared images at nighttime. To validate the effectiveness of the proposed method, two groups of experiments, namely, railway and non-railway scenes, are conducted. Experimental results demonstrate the effectiveness of the proposed method, and an improvement of 17.8% is achieved for object detection at nighttime.

scholarly journals Dynamics of Fourier Modes in Torus Generative Adversarial Networks

Mathematics ◽  
2021 ◽  
Vol 9 (4) ◽  
pp. 325
Author(s):  
Ángel González-Prieto ◽  
Alberto Mozo ◽  
Edgar Talavera ◽  
Sandra Gómez-Canaval
Keyword(s):  
Fourier Series ◽  
Generative Adversarial Networks ◽  
Learning Models ◽  
Training Process ◽  
Small Perturbations ◽  
Adversarial Networks ◽  
Novel Method ◽  
Truncated Fourier Series ◽  
Real Flow ◽  
Machine Learning Models

Generative Adversarial Networks (GANs) are powerful machine learning models capable of generating fully synthetic samples of a desired phenomenon with a high resolution. Despite their success, the training process of a GAN is highly unstable, and typically, it is necessary to implement several accessory heuristics to the networks to reach acceptable convergence of the model. In this paper, we introduce a novel method to analyze the convergence and stability in the training of generative adversarial networks. For this purpose, we propose to decompose the objective function of the adversary min–max game defining a periodic GAN into its Fourier series. By studying the dynamics of the truncated Fourier series for the continuous alternating gradient descend algorithm, we are able to approximate the real flow and to identify the main features of the convergence of GAN. This approach is confirmed empirically by studying the training flow in a 2-parametric GAN, aiming to generate an unknown exponential distribution. As a by-product, we show that convergent orbits in GANs are small perturbations of periodic orbits so the Nash equillibria are spiral attractors. This theoretically justifies the slow and unstable training observed in GANs.

Towards Accuracy Enhancement of Age Group Classification Using Generative Adversarial Networks

2021 ◽  
pp. 1-17
Author(s):  
Khaled ELKarazle ◽  
Valliappan Raman ◽  
Patrick Then
Keyword(s):  
Age Estimation ◽  
Super Resolution ◽  
Generative Adversarial Networks ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Adversarial Networks ◽  
Original Dataset ◽  
Age Group Classification ◽  
Facial Images

Age estimation models can be employed in many applications, including soft biometrics, content access control, targeted advertising, and many more. However, as some facial images are taken in unrestrained conditions, the quality relegates, which results in the loss of several essential ageing features. This study investigates how introducing a new layer of data processing based on a super-resolution generative adversarial network (SRGAN) model can influence the accuracy of age estimation by enhancing the quality of both the training and testing samples. Additionally, we introduce a novel convolutional neural network (CNN) classifier to distinguish between several age classes. We train one of our classifiers on a reconstructed version of the original dataset and compare its performance with an identical classifier trained on the original version of the same dataset. Our findings reveal that the classifier which trains on the reconstructed dataset produces better classification accuracy, opening the door for more research into building data-centric machine learning systems.

scholarly journals Improving Skin Lesion Analysis with Generative Adversarial Networks

2020 ◽  
Author(s):  
Alceu Bissoto ◽  
Sandra Avila
Keyword(s):  
Skin Lesion ◽  
State Of The Art ◽  
Synthetic Data ◽  
Clinical Information ◽  
Analysis Data ◽  
Training Dataset ◽  
Generative Adversarial Networks ◽  
Classification Models ◽  
Adversarial Networks ◽  
Lesion Analysis

Melanoma is the most lethal type of skin cancer. Early diagnosis is crucial to increase the survival rate of those patients due to the possibility of metastasis. Automated skin lesion analysis can play an essential role by reaching people that do not have access to a specialist. However, since deep learning became the state-of-the-art for skin lesion analysis, data became a decisive factor in pushing the solutions further. The core objective of this M.Sc. dissertation is to tackle the problems that arise by having limited datasets. In the first part, we use generative adversarial networks to generate synthetic data to augment our classification model’s training datasets to boost performance. Our method generates high-resolution clinically-meaningful skin lesion images, that when compound our classification model’s training dataset, consistently improved the performance in different scenarios, for distinct datasets. We also investigate how our classification models perceived the synthetic samples and how they can aid the model’s generalization. Finally, we investigate a problem that usually arises by having few, relatively small datasets that are thoroughly re-used in the literature: bias. For this, we designed experiments to study how our models’ use data, verifying how it exploits correct (based on medical algorithms), and spurious (based on artifacts introduced during image acquisition) correlations. Disturbingly, even in the absence of any clinical information regarding the lesion being diagnosed, our classification models presented much better performance than chance (even competing with specialists benchmarks), highly suggesting inflated performances.

scholarly journals Fractional Wavelet-Based Generative Scattering Networks

2021 ◽  
Vol 15 ◽  
Author(s):  
Jiasong Wu ◽  
Xiang Qiu ◽  
Jing Zhang ◽  
Fuzhi Wu ◽  
Youyong Kong ◽  
...  
Keyword(s):  
Dimensionality Reduction ◽  
Reduction Method ◽  
Gaussian White Noise ◽  
Principal Component ◽  
Experimental Results ◽  
Generative Adversarial Networks ◽  
Image Generation ◽  
Adversarial Networks ◽  
Dimensionality Reduction Method

Generative adversarial networks and variational autoencoders (VAEs) provide impressive image generation from Gaussian white noise, but both are difficult to train, since they need a generator (or encoder) and a discriminator (or decoder) to be trained simultaneously, which can easily lead to unstable training. To solve or alleviate these synchronous training problems of generative adversarial networks (GANs) and VAEs, researchers recently proposed generative scattering networks (GSNs), which use wavelet scattering networks (ScatNets) as the encoder to obtain features (or ScatNet embeddings) and convolutional neural networks (CNNs) as the decoder to generate an image. The advantage of GSNs is that the parameters of ScatNets do not need to be learned, while the disadvantage of GSNs is that their ability to obtain representations of ScatNets is slightly weaker than that of CNNs. In addition, the dimensionality reduction method of principal component analysis (PCA) can easily lead to overfitting in the training of GSNs and, therefore, affect the quality of generated images in the testing process. To further improve the quality of generated images while keeping the advantages of GSNs, this study proposes generative fractional scattering networks (GFRSNs), which use more expressive fractional wavelet scattering networks (FrScatNets), instead of ScatNets as the encoder to obtain features (or FrScatNet embeddings) and use similar CNNs of GSNs as the decoder to generate an image. Additionally, this study develops a new dimensionality reduction method named feature-map fusion (FMF) instead of performing PCA to better retain the information of FrScatNets,; it also discusses the effect of image fusion on the quality of the generated image. The experimental results obtained on the CIFAR-10 and CelebA datasets show that the proposed GFRSNs can lead to better generated images than the original GSNs on testing datasets. The experimental results of the proposed GFRSNs with deep convolutional GAN (DCGAN), progressive GAN (PGAN), and CycleGAN are also given.

scholarly journals Multi-Turn Chatbot Based on Query-Context Attentions and Dual Wasserstein Generative Adversarial Networks

2019 ◽  
Vol 9 (18) ◽  
pp. 3908 ◽  
Author(s):  
Jintae Kim ◽  
Shinhyeok Oh ◽  
Oh-Woog Kwon ◽  
Harksoo Kim
Keyword(s):  
Performance Measures ◽  
State Of The Art ◽  
Attention Mechanism ◽  
Generative Adversarial Networks ◽  
Training Method ◽  
Adversarial Networks ◽  
Proposed Model ◽  
Previous State ◽  
Vector Representations

To generate proper responses to user queries, multi-turn chatbot models should selectively consider dialogue histories. However, previous chatbot models have simply concatenated or averaged vector representations of all previous utterances without considering contextual importance. To mitigate this problem, we propose a multi-turn chatbot model in which previous utterances participate in response generation using different weights. The proposed model calculates the contextual importance of previous utterances by using an attention mechanism. In addition, we propose a training method that uses two types of Wasserstein generative adversarial networks to improve the quality of responses. In experiments with the DailyDialog dataset, the proposed model outperformed the previous state-of-the-art models based on various performance measures.

Sign in / Sign up

Export Citation Format

Share Document