scholarly journals Simplified Fréchet Distance for Generative Adversarial Nets

Sensors ◽  
2020 ◽  
Vol 20 (6) ◽  
pp. 1548 ◽  
Author(s):  
Chung-Il Kim ◽  
Meejoung Kim ◽  
Seungwon Jung ◽  
Eenjun Hwang
Keyword(s):  
Real Data ◽  
Experimental Results ◽  
Loss Functions ◽  
Distance Metrics ◽  
Fréchet Distance ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Frechet Distance ◽  
Boundary Equilibrium ◽  
Covariance Term

We introduce a distance metric between two distributions and propose a Generative Adversarial Network (GAN) model: the Simplified Fréchet distance (SFD) and the Simplified Fréchet GAN (SFGAN). Although the data generated through GANs are similar to real data, GAN often undergoes unstable training due to its adversarial structure. A possible solution to this problem is considering Fréchet distance (FD). However, FD is unfeasible to realize due to its covariance term. SFD overcomes the complexity so that it enables us to realize in networks. The structure of SFGAN is based on the Boundary Equilibrium GAN (BEGAN) while using SFD in loss functions. Experiments are conducted with several datasets, including CelebA and CIFAR-10. The losses and generated samples of SFGAN and BEGAN are compared with several distance metrics. The evidence of mode collapse and/or mode drop does not occur until 3000k steps for SFGAN, while it occurs between 457k and 968k steps for BEGAN. Experimental results show that SFD makes GANs more stable than other distance metrics used in GANs, and SFD compensates for the weakness of models based on BEGAN-based network structure. Based on the experimental results, we can conclude that SFD is more suitable for GAN than other metrics.

Technique for Removing Unnecessary Superimposed Patterns from Image using Generative Network

2021 ◽  
Author(s):  
Kazutake Uehira ◽  
Hiroshi Unno
Keyword(s):  
Color Image ◽  
Depth Map ◽  
Experimental Results ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Blue Component ◽  
Component Image

A technique for removing unnecessary patterns from captured images by using a generative network is studied. The patterns, composed of lines and spaces, are superimposed onto a blue component image of RGB color image when the image is captured for the purpose of acquiring a depth map. The superimposed patterns become unnecessary after the depth map is acquired. We tried to remove these unnecessary patterns by using a generative adversarial network (GAN) and an auto encoder (AE). The experimental results show that the patterns can be removed by using a GAN and AE to the point of being invisible. They also show that the performance of GAN is much higher than that of AE and that its PSNR and SSIM were over 45 and about 0.99, respectively. From the results, we demonstrate the effectiveness of the technique with a GAN.

scholarly journals 1D conditional generative adversarial network for spectrum-to-spectrum translation of simulated chemical reflectance signatures

2021 ◽  
Author(s):  
Cara Murphy ◽  
John Kerekes
Keyword(s):  
Classification Accuracy ◽  
Domain Adaptation ◽  
Real Data ◽  
Training Set ◽  
Generative Adversarial Network ◽  
Average Classification Accuracy ◽  
Adversarial Network ◽  
Chemical Residues ◽  
Reflectance Data

The classification of trace chemical residues through active spectroscopic sensing is challenging due to the lack of physics-based models that can accurately predict spectra. To overcome this challenge, we leveraged the field of domain adaptation to translate data from the simulated to the measured domain for training a classifier. We developed the first 1D conditional generative adversarial network (GAN) to perform spectrum-to-spectrum translation of reflectance signatures. We applied the 1D conditional GAN to a library of simulated spectra and quantified the improvement in classification accuracy on real data using the translated spectra for training the classifier. Using the GAN-translated library, the average classification accuracy increased from 0.622 to 0.723 on real chemical reflectance data, including data from chemicals not included in the GAN training set.

scholarly journals JANE: Jointly Adversarial Network Embedding

2020 ◽  
Author(s):  
Liang Yang ◽  
Yuexue Wang ◽  
Junhua Gu ◽  
Chuan Wang ◽  
Xiaochun Cao ◽  
...  
Keyword(s):  
Link Prediction ◽  
Real Data ◽  
Semantic Space ◽  
Network Embedding ◽  
Generative Adversarial Network ◽  
Adversarial Learning ◽  
Adversarial Network ◽  
Node Clustering ◽  
Topology Information ◽  
Embedding Methods

Motivated by the capability of Generative Adversarial Network on exploring the latent semantic space and capturing semantic variations in the data distribution, adversarial learning has been adopted in network embedding to improve the robustness. However, this important ability is lost in existing adversarially regularized network embedding methods, because their embedding results are directly compared to the samples drawn from perturbation (Gaussian) distribution without any rectification from real data. To overcome this vital issue, a novel Joint Adversarial Network Embedding (JANE) framework is proposed to jointly distinguish the real and fake combinations of the embeddings, topology information and node features. JANE contains three pluggable components, Embedding module, Generator module and Discriminator module. The overall objective function of JANE is defined in a min-max form, which can be optimized via alternating stochastic gradient. Extensive experiments demonstrate the remarkable superiority of the proposed JANE on link prediction (3% gains in both AUC and AP) and node clustering (5% gain in F1 score).

Sound Field Reconstruction in Rooms with Deep Generative Models

2021 ◽  
Vol 263 (5) ◽  
pp. 1527-1538
Author(s):  
Xenofon Karakonstantis ◽  
Efren Fernandez Grande
Keyword(s):  
Plane Waves ◽  
Sound Field ◽  
Real Data ◽  
Generative Models ◽  
Random Wave ◽  
Generative Adversarial Network ◽  
Underlying Distribution ◽  
Adversarial Network ◽  
Reconstruction Methods ◽  
Free Region

The characterization of Room Impulse Responses (RIR) over an extended region in a room by means of measurements requires dense spatial with many microphones. This can often become intractable and time consuming in practice. Well established reconstruction methods such as plane wave regression show that the sound field in a room can be reconstructed from sparsely distributed measurements. However, these reconstructions usually rely on assuming physical sparsity (i.e. few waves compose the sound field) or trait in the measured sound field, making the models less generalizable and problem specific. In this paper we introduce a method to reconstruct a sound field in an enclosure with the use of a Generative Adversarial Network (GAN), which s new variants of the data distributions that it is trained upon. The goal of the proposed GAN model is to estimate the underlying distribution of plane waves in any source free region, and map these distributions from a stochastic, latent representation. A GAN is trained on a large number of synthesized sound fields represented by a random wave field and then tested on both simulated and real data sets, of lightly damped and reverberant rooms.

scholarly journals Separating Chinese Character from Noisy Background Using GAN

2021 ◽  
Vol 2021 ◽  
pp. 1-13
Author(s):  
Bin Huang ◽  
Jiaqi Lin ◽  
Jinming Liu ◽  
Jie Chen ◽  
Jiemin Zhang ◽  
...  
Keyword(s):  
Character Recognition ◽  
Optical Character Recognition ◽  
Complex Structure ◽  
Real Data ◽  
Semantic Segmentation ◽  
Chinese Characters ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Basic Network ◽  
Noisy Background

Separating printed or handwritten characters from a noisy background is valuable for many applications including test paper autoscoring. The complex structure of Chinese characters makes it difficult to obtain the goal because of easy loss of fine details and overall structure in reconstructed characters. This paper proposes a method for separating Chinese characters based on generative adversarial network (GAN). We used ESRGAN as the basic network structure and applied dilated convolution and a novel loss function that improve the quality of reconstructed characters. Four popular Chinese fonts (Hei, Song, Kai, and Imitation Song) on real data collection were tested, and the proposed design was compared with other semantic segmentation approaches. The experimental results showed that the proposed method effectively separates Chinese characters from noisy background. In particular, our methods achieve better results in terms of Intersection over Union (IoU) and optical character recognition (OCR) accuracy.

scholarly journals Event Factuality Identification via Generative Adversarial Networks with Auxiliary Classification

2018 ◽  
Author(s):  
Zhong Qian ◽  
Peifeng Li ◽  
Yue Zhang ◽  
Guodong Zhou ◽  
Qiaoming Zhu
Keyword(s):  
State Of The Art ◽  
Experimental Results ◽  
Generative Adversarial Networks ◽  
Semantic Task ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Adversarial Networks ◽  
Traditional Research ◽  
Syntactic Information ◽  
Event Factuality

Event factuality identification is an important semantic task in NLP. Traditional research heavily relies on annotated texts. This paper proposes a two-step framework, first extracting essential factors related with event factuality from raw texts as the input, and then identifying the factuality of events via a Generative Adversarial Network with Auxiliary Classification (AC-GAN). The use of AC-GAN allows the model to learn more syntactic information and address the imbalance among factuality values. Experimental results on FactBank show that our method significantly outperforms several state-of-the-art baselines, particularly on events with embedded sources, speculative and negative factuality values.

scholarly journals Image Completion with Large or Edge-Missing Areas

Algorithms ◽  
2019 ◽  
Vol 13 (1) ◽  
pp. 14
Author(s):  
Jianjian Ji ◽  
Gang Yang
Keyword(s):  
Experimental Results ◽  
The Other ◽  
Context Information ◽  
Network Structures ◽  
Image Completion ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Other Hand ◽  
The One ◽  
Pseudo Color

Existing image completion methods are mostly based on missing regions that are small or located in the middle of the images. When regions to be completed are large or near the edge of the images, due to the lack of context information, the completion results tend to be blurred or distorted, and there will be a large blank area in the final results. In addition, the unstable training of the generative adversarial network is also prone to cause pseudo-color in the completion results. Aiming at the two above-mentioned problems, a method of image completion with large or edge-missing areas is proposed; also, the network structures have been improved. On the one hand, it overcomes the problem of lacking context information, which thereby ensures the reality of generated texture details; on the other hand, it suppresses the generation of pseudo-color, which guarantees the consistency of the whole image both in vision and content. The experimental results show that the proposed method achieves better completion results in completing large or edge-missing areas.

scholarly journals Data Augmentation of Backscatter X-ray Images for Deep Learning-Based Automatic Cargo Inspection

Sensors ◽  
2021 ◽  
Vol 21 (21) ◽  
pp. 7294
Author(s):  
Hyunwoo Cho ◽  
Haesol Park ◽  
Ig-Jae Kim ◽  
Junghyun Cho
Keyword(s):  
Data Augmentation ◽  
Image Data ◽  
Real Data ◽  
Generative Adversarial Network ◽  
X Ray ◽  
Domain Specific ◽  
Adversarial Network ◽  
Vehicle Data ◽  
Cargo Inspection ◽  
Special Modification

Custom inspection using X-ray imaging is a very promising application of modern pattern recognition technology. However, the lack of data or renewal of tariff items makes the application of such technology difficult. In this paper, we present a data augmentation technique based on a new image-to-image translation method to deal with these difficulties. Unlike the conventional methods that convert a semantic label image into a realistic image, the proposed method takes a texture map with a special modification as an additional input of a generative adversarial network to reproduce domain-specific characteristics, such as background clutter or sensor-specific noise patterns. The proposed method was validated by applying it to backscatter X-ray (BSX) vehicle data augmentation. The Fréchet inception distance (FID) of the result indicates the visual quality of the translated image was significantly improved from the baseline when the texture parameters were used. Additionally, in terms of data augmentation, the experimental results of classification, segmentation, and detection show that the use of the translated image data, along with the real data consistently, improved the performance of the trained models. Our findings show that detailed depiction of the texture in translated images is crucial for data augmentation. Considering the comparatively few studies that have examined custom inspections of container scale goods, such as cars, we believe that this study will facilitate research on the automation of container screening, and the security of aviation and ports.

scholarly journals Realizing the Application of EEG Modeling in BCI Classification: Based on a Conditional GAN Converter

2021 ◽  
Vol 15 ◽  
Author(s):  
Xiaodong Zhang ◽  
Zhufeng Lu ◽  
Teng Zhang ◽  
Hanzhe Li ◽  
Yachun Wang ◽  
...  
Keyword(s):  
Test Performance ◽  
Real Data ◽  
Neural Mass Model ◽  
Mass Model ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Equivalent Dipole ◽  
Neural Mass ◽  
Qualitative Level ◽  
Surface Eeg

Electroencephalogram (EEG) modeling in brain-computer interface (BCI) provides a theoretical foundation for its development. However, limited by the lack of guidelines in model parameter selection and the inability to obtain personal tissue information in practice, EEG modeling in BCI is mainly focused on the theoretical qualitative level which shows a gap between the theory and its application. Based on such problems, this work combined the surface EEG simulation with a converter based on the generative adversarial network (GAN), to establish the connection from simulated EEG to its application in BCI classification. For the scalp EEGs modeling, a mathematical model was built according to the physics of surface EEG, which consisted of the parallel 3-population neural mass model, the equivalent dipole, and the forward computation. For application, a converter based on the conditional GAN was designed, to transfer the simulated theoretical-only EEG to its practical version, in the lack of individual bio-information. To verify the feasibility, based on the latest microexpression-assisted BCI paradigm proposed by our group, the converted simulated EEGs were used in the training of BCI classifiers. The results indicated that, compared with training with insufficient real data, by adding the simulated EEGs, the overall performance showed a significant improvement (P = 0.04 < 0.05), and the test performance can be improved by 2.17% ± 4.23, in which the largest increase was up to 12.60% ± 1.81. Through this work, the link from theoretical EEG simulation to BCI classification has been initially established, providing an enhanced novel solution for the application of EEG modeling in BCI.

scholarly journals Analysis and Validation of Cross-Modal Generative Adversarial Network for Sensory Substitution

2021 ◽  
Vol 18 (12) ◽  
pp. 6216
Author(s):  
Mooseop Kim ◽  
YunKyung Park ◽  
KyeongDeok Moon ◽  
Chi Yoon Jeong
Keyword(s):  
Visual Information ◽  
Experimental Results ◽  
Auditory Sensitivity ◽  
Sensory Substitution ◽  
Sensitivity Analyses ◽  
Auditory Signal ◽  
Behavioral Experiments ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Proposed Model

Visual-auditory sensory substitution has demonstrated great potential to help visually impaired and blind groups to recognize objects and to perform basic navigational tasks. However, the high latency between visual information acquisition and auditory transduction may contribute to the lack of the successful adoption of such aid technologies in the blind community; thus far, substitution methods have remained only laboratory-scale research or pilot demonstrations. This high latency for data conversion leads to challenges in perceiving fast-moving objects or rapid environmental changes. To reduce this latency, prior analysis of auditory sensitivity is necessary. However, existing auditory sensitivity analyses are subjective because they were conducted using human behavioral analysis. Therefore, in this study, we propose a cross-modal generative adversarial network-based evaluation method to find an optimal auditory sensitivity to reduce transmission latency in visual-auditory sensory substitution, which is related to the perception of visual information. We further conducted a human-based assessment to evaluate the effectiveness of the proposed model-based analysis in human behavioral experiments. We conducted experiments with three participant groups, including sighted users (SU), congenitally blind (CB) and late-blind (LB) individuals. Experimental results from the proposed model showed that the temporal length of the auditory signal for sensory substitution could be reduced by 50%. This result indicates the possibility of improving the performance of the conventional vOICe method by up to two times. We confirmed that our experimental results are consistent with human assessment through behavioral experiments. Analyzing auditory sensitivity with deep learning models has the potential to improve the efficiency of sensory substitution.

Sign in / Sign up

Export Citation Format

Share Document