Discriminator Of Generative Adversarial Network Research Articles

DGRM: Diffusion-GAN recommendation model to alleviate the mode collapse problem in sparse environments

Generative adversarial network (GAN) has been widely adopted in recommender systems (RSs) to improve the recommendation accuracy. However, existing GAN-based models often suffer from the mode collapse problem in sparse environments and fail to adequately capture the complexity of user preferences and behaviors, which affects recommendation performance. To address these issues, we introduce a diffusion model (DM) into the GAN framework, proposing an efficient Diffusion-GAN recommendation model (DGRM) to achieve mutual enhancement between the two generative models. This model first utilizes the forward process of DM to generate conditional vectors that guide the training of the GAN generator. Subsequently, the backward process of DM assists the GAN discriminator using Wasserstein distance during adversarial training. The Wasserstein distance is adopted to solve the asymmetry of Kullback-Leibler (KL) divergence as a loss function in traditional GANs. Experiments on multiple datasets demonstrate that the proposed model effectively alleviates mode collapse and surpasses other state-of-the-art (SOTA) methods in various evaluation metrics.

Time–Frequency Domain Seismic Signal Denoising Based on Generative Adversarial Networks

Existing deep learning-based seismic signal denoising methods primarily operate in the time domain. Those methods are ineffective when noise overlaps with the seismic signal in the time domain. Time–frequency domain-based deep learning methods are relatively rare and usually employ single loss function, resulting in suboptimal performance on low SNR signals and potential damage to P wave. This paper proposes a method based on generative adversarial networks (GANs). Compared to convolutional neural networks, the discriminator in GANs helps retain more true signal details by judging denoising performance. Additionally, an attention mechanism is introduced to fully extract signal features, and a perceptual loss is employed to evaluate the difference between the denoised result and the target’s high-level features. Experimental results show that this method can effectively improve SNR and ensure that the denoised result is close to the true signal. Furthermore, by comparing DeepDenoiser and ARDU, it is proven that the proposed method achieves better denoising performance, especially for low SNR signals, while causing less damage to the seismic signals.

Offline Data-Driven Multiobjective Optimization Evolutionary Algorithm Based on Generative Adversarial Network

Usually, data-driven multi-objective optimiza -tion problems (DD-MOPs) are indirectly solved by evolutionary algorithms through the built surrogate model which is well-trained from sample data. However, in most DD-MOPs, only a few available data can be practicably collected from real engineering experiments due to the unaffordable cost and time. The key challenge in such a DD-MOP is to prevent the serious deterioration on the accuracy of the obtained approximate Pareto front. In this paper, two novel strategies, critical fitness for evolutionary algorithms and data augmentation for a surrogate model, are complementarily imposed by a generative adversarial network (GAN) to tackle with the challenges in DD-MOPs. In the critical fitness strategy, a new critical fitness, composed of the critical score from the discriminator of GAN and the prediction value of surrogate model, is proposed to improve the accuracy of approximate Pareto front of a DD-MOP. In the data augmentation strategy, some new samples are synthetized by the generator of GAN to build a better-trained surrogate model. As a result, the GAN concurrently serves the critical fitness strategy and the data augmentation strategy as the roles of “killing two birds with one stone”. The performance of the proposed algorithm for DD-MOPs was well-verified over 26 benchmark problems and successfully applied to discover new NdFeB materials.

Discriminative Forests Improve Generative Diversity for Generative Adversarial Networks

Improving the diversity of Artificial Intelligence Generated Content (AIGC) is one of the fundamental problems in the theory of generative models such as generative adversarial networks (GANs). Previous studies have demonstrated that the discriminator in GANs should have high capacity and robustness to achieve the diversity of generated data. However, a discriminator with high capacity tends to overfit and guide the generator toward collapsed equilibrium. In this study, we propose a novel discriminative forest GAN, named Forest-GAN, that replaces the discriminator to improve the capacity and robustness for modeling statistics in real-world data distribution. A discriminative forest is composed of multiple independent discriminators built on bootstrapped data. We prove that a discriminative forest has a generalization error bound, which is determined by the strength of individual discriminators and the correlations among them. Hence, a discriminative forest can provide very large capacity without any risk of overfitting, which subsequently improves the generative diversity. With the discriminative forest framework, we significantly improved the performance of AutoGAN with a new record FID of 19.27 from 30.71 on STL10 and improved the performance of StyleGAN2-ADA with a new record FID of 6.87 from 9.22 on LSUN-cat.

RDP-GAN: A Rényi-Differential Privacy Based Generative Adversarial Network

Generative adversarial networks (GANs) have attracted increasing attention recently owing to their impressive abilities to generate realistic samples with high privacy protection. Without directly interacting with training examples, the generative model can be used to estimate the underlying distribution of an original dataset while the discriminator can examine model quality of the generated samples by comparing the label values with training examples. In considering privacy issues in GANS, existing works focus on perturbing the parameters and analyzing the corresponding privacy protection capability, and the parameters are not directly exchanged between the generator and discriminator in GANs. Thus, in this work, we propose a Rényi-differentially private-GAN (RDP-GAN), which achieves differential privacy (DP) in a GAN by carefully adding random Gaussian noise to the value of the exchanged loss function during training. Moreover, we derive analytical results characterizing the total privacy loss under the subsampling method and cumulative iterations, which show its effectiveness for the privacy budget allocation. In addition, in order to mitigate the negative impact of injecting noises, we enhance the proposed algorithm by adding an adaptive noise tuning step, which will change the amount of added noise according to the testing accuracy. Through extensive experimental results, we verify that the proposed algorithm can achieve a better privacy level while producing high-quality samples compared with a benchmark DP-GAN scheme based on noise perturbation on training gradients.

Underwater Wireless Optical Communication With One-Bit Quantization: A Hybrid Autoencoder and Generative Adversarial Network Approach

Compared with underwater acoustic communication, underwater wireless optical communication (UWOC) has the advantages of wide communication bandwidth, high transmission speed and strong directional transmission, which make it have broad application prospects. However, the absorption and scattering effects in underwater environments cause a UWOC system to suffer from severe channel fading. To reduce the system complexity and power loss, the on–off-keying (OOK) modulation scheme and one-bit analog-to-digital converter are considered in this work. Besides, to deal with the complex underwater optical channels and the nonlinearity of the one-bit quantization, a novel deep learning based architecture integrating the autoencoder (AE) and generative adversarial network (GAN), named hybrid AE-GAN, is developed. In the proposed hybrid AE-GAN, the generator in GAN is responsible for a generalized channel equalization, which aims to equalize both the impairments from underwater optical channels and the distortion from one-bit quantization. While the decoder in AE and the discriminator in GAN share the same network to distinguish true and fake as well as reconstruct the sent messages simultaneously. Meanwhile, the one-bit quantized signal is regarded as conditional information for GAN to assist in targeted channel equalization for various signals. Moreover, a specialized loss function and training strategy for the hybrid AE-GAN are also presented, which can optimize AE and GAN at the same time, and deal with the problem that the binarization of OOK stymies the gradient backpropagation. The simulation results indicate that the proposed hybrid AE-GAN can achieve superior performance.

Swgan: A new algorithm of adhesive rice image segmentation based on improved generative adversarial networks

Image segmentation is a crucial part in the automatic detection of rice appearance quality. Due to morphological characteristics of rice grains, missed detection and non-smooth boundaries may exist in the image segmentation of adhesive rice. To address the above issues, this study proposes a novel model named Swgan combined generative adversarial networks (GANs) with nested skip connections for obtaining accurate masks. In order to learn the mask distribution of each object in adhesive rice image and further avoid missed detection, the discriminator in GAN is used as a modifier of Cascade Mask R-CNN model to allow the generator to overcome the limitation of mask generation training, namely detecting multiply objects as a single target. Moreover, the Swgan utilizes Swin-Transformer as the backbone network and incorporates the Cascade Mask R-CNN framework and Nested Feature Pyramid Network (Nested-FPN) to maintain the mask’s boundary smoothness during forward propagation. Experimental results indicate that the Swgan is used to obtain better segmentation results from objective detection and segmentation under complex conditions of adhesive rice when compared with state-of-art algorithms. Overall, the Swgan with satisfactory accuracy in image segmentation of adhesive rice combined with physical indicators detection provide reliable quality assessment of rice grains.

CoopInit: Initializing Generative Adversarial Networks via Cooperative Learning

Numerous research efforts have been made to stabilize the training of the Generative Adversarial Networks (GANs), such as through regularization and architecture design. However, we identify the instability can also arise from the fragile balance at the early stage of adversarial learning. This paper proposes the CoopInit, a simple yet effective cooperative learning-based initialization strategy that can quickly learn a good starting point for GANs, with a very small computation overhead during training. The proposed algorithm consists of two learning stages: (i) Cooperative initialization stage: The discriminator of GAN is treated as an energy-based model (EBM) and is optimized via maximum likelihood estimation (MLE), with the help of the GAN's generator to provide synthetic data to approximate the learning gradients. The EBM also guides the MLE learning of the generator via MCMC teaching; (ii) Adversarial finalization stage: After a few iterations of initialization, the algorithm seamlessly transits to the regular mini-max adversarial training until convergence. The motivation is that the MLE-based initialization stage drives the model towards mode coverage, which is helpful in alleviating the issue of mode dropping during the adversarial learning stage. We demonstrate the effectiveness of the proposed approach on image generation and one-sided unpaired image-to-image translation tasks through extensive experiments.

The Deep Learning Generative Adversarial Random Neural Network in data marketplaces: The digital creative

Generative Adversarial Networks (GANs) have been proposed as a method to generate multiple replicas from an original version combining a Discriminator and a Generator. The main applications of GANs have been the casual generation of audio and video content. GANs, as a neural method that generates populations of individuals, have emulated genetic algorithms based on biologically inspired operators such as mutation, crossover and selection. This article presents the Deep Learning Generative Adversarial Random Neural Network (RNN) with the same features and functionality as a GAN. Furthermore, the presented algorithm is proposed for an application, the Digital Creative, that generates tradeable replicas in a Data Marketplace, such as 1D functions or audio, 2D and 3D images and video content. The RNN Generator creates individuals mapped from a latent space while the GAN Discriminator evaluates them based on the true data distribution. The performance of the Deep Learning Generative Adversarial RNN has been assessed against several input vectors with different dimensions, in addition to 1D functions and 2D images. The presented results are successful: the learning objective of the RNN Generator creates tradeable replicas at low error, whereas the RNN Discriminator learning target identifies unfit individuals.

Exploring the Advantages of Quantum Generative Adversarial Networks in Generative Chemistry.

De novo drug design with desired biological activities is crucial for developing novel therapeutics for patients. The drug development process is time- and resource-consuming, and it has a low probability of success. Recent advances in machine learning and deep learning technology have reduced the time and cost of the discovery process and therefore, improved pharmaceutical research and development. In this paper, we explore the combination of two rapidly developing fields with lead candidate discovery in the drug development process. First, artificial intelligence has already been demonstrated to successfully accelerate conventional drug design approaches. Second, quantum computing has demonstrated promising potential in different applications, such as quantum chemistry, combinatorial optimizations, and machine learning. This article explores hybrid quantum-classical generative adversarial networks (GAN) for small molecule discovery. We substituted each element of GAN with a variational quantum circuit (VQC) and demonstrated the quantum advantages in the small drug discovery. Utilizing a VQC in the noise generator of a GAN to generate small molecules achieves better physicochemical properties and performance in the goal-directed benchmark than the classical counterpart. Moreover, we demonstrate the potential of a VQC with only tens of learnable parameters in the generator of GAN to generate small molecules. We also demonstrate the quantum advantage of a VQC in the discriminator of GAN. In this hybrid model, the number of learnable parameters is significantly less than the classical ones, and it can still generate valid molecules. The hybrid model with only tens of training parameters in the quantum discriminator outperforms the MLP-based one in terms of both generated molecule properties and the achieved KL divergence. However, the hybrid quantum-classical GANs still face challenges in generating unique and valid molecules compared to their classical counterparts.

Reconstruction of missing shear wave slowness in shale gas reservoir based on deep learning algorithm

Shear wave slowness (DTS) is a significant data for reservoir evaluation and description. Due to the cost and time-consuming, the missing of DTS is inevitable in well logging. Empirical equations and traditional machine learning methods are often used to estimate the general trend of DTS, but their ability to predict the local details is limited, which is particularly important for highly heterogeneous reservoirs such as shale. In this paper, based on the generative adversarial network (GAN), a new deep learning model was established for DTS reconstruction, in which the long short-term memory network (LSTM) was applied as the generator to learn the overall trend of logging data and generate pseudo DTS sequence, the one-dimensional convolutional neural network (1DCNN) was applied as the discriminator to capture the local details of logging data and judge the authenticity of DTS sequence. The generator and discriminator in GAN were trained at the same time to achieve model convergence and the high distribution similarity between reconstructed DTS and the real one. Several data experiments were conducted with the logging data of 102 wells from Weiyuan shale gas field, China, and the proposed model were proved to have good prediction ability for both the overall fluctuation and local details of DTS logging data. The processing flow recommended in this paper provides an economic and fast choice for the reconstruction of missing DTS in shale gas reservoir and shows the potential of applying deep learning algorithm in assisting logging data generation.

Applying a GAN-based classifier to improve transcriptome-based prognostication in breast cancer.

Established prognostic tests based on limited numbers of transcripts can identify high-risk breast cancer patients, yet are approved only for individuals presenting with specific clinical features or disease characteristics. Deep learning algorithms could hold potential for stratifying patient cohorts based on full transcriptome data, yet the development of robust classifiers is hampered by the number of variables in omics datasets typically far exceeding the number of patients. To overcome this hurdle, we propose a classifier based on a data augmentation pipeline consisting of a Wasserstein generative adversarial network (GAN) with gradient penalty and an embedded auxiliary classifier to obtain a trained GAN discriminator (T-GAN-D). Applied to 1244 patients of the METABRIC breast cancer cohort, this classifier outperformed established breast cancer biomarkers in separating low- from high-risk patients (disease specific death, progression or relapse within 10 years from initial diagnosis). Importantly, the T-GAN-D also performed across independent, merged transcriptome datasets (METABRIC and TCGA-BRCA cohorts), and merging data improved overall patient stratification. In conclusion, the reiterative GAN-based training process allowed generating a robust classifier capable of stratifying low- vs high-risk patients based on full transcriptome data and across independent and heterogeneous breast cancer cohorts.

Reconstructing Images Through Multimode Fibers From the Up-Conversion Speckle Patterns via Deep Learning

The mode mixing and mode dispersion in the multimode fiber (MMF) will produce complex speckle patterns in the distal end of the fiber as an object passes through the MMF, rendering image reconstruction to be a challenging task. In recent years, convolutional neural networks have been successfully applied to image reconstruction from speckles. However, the imaging spectra of these studies are mostly in the visible spectrum range and require complete speckle information for reconstruction. In this paper, researchers build an optical imaging system that employs up-conversion imaging technology to collect speckle patterns generated by infrared light transmitting through a multimode fiber and a frequency-doubling crystal. They propose a speckle restoration network (SRNet) based on a generative adversarial network (GAN) to reconstruct speckle images. The generator of GAN uses ResNest and atrous spatial pyramid pooling (ASPP) to extract multi-level features and multi-scale context information, respectively. The discriminator of GAN significantly improves the quality of the reconstructed image generated by the generator. In addition, researchers adopt a special training method named pre-training generator to avoid gradient disappearance or gradient explosion in the training process. With the designed network, high-quality images were successfully reconstructed even with only a portion of the speckle information.

A prediction model of stock market trading actions using generative adversarial network and piecewise linear representation approaches.

Supervised learning applied stock prediction tasks and obtained satisfactory performance. The trading strategies are very complex and diverse but supervised learning is only learned and fitted by gold standard trading strategies. Supervised learning approaches often have over-fitting problems. To learn distribution of gold standard answers, the generative adversarial network (GAN) models can generate extra similar samples to improve performance. Therefore, the paper proposes a generative GAN-based frameworks with the piecewise linear representation (PLR) approach to learn three trading actions, namely buying, selling, and holding. The proposed framework consists of two parts: first, PLR approach uses to detect historical prices to form trading sequences with three actions, PLR can provide a guided trading strategy to discriminator of GAN. Second, the generator of GAN is used to generate/predict daily trading actions, and the discriminator is used to detect the real/fake trading actions from the PLR/generator of GAN. Experimental results indicate that the proposed GAN-based frameworks outperform the long short-term memory network.

LUMDE: Light-Weight Unsupervised Monocular Depth Estimation via Knowledge Distillation

The use of the unsupervised monocular depth estimation network approach has seen rapid progress in recent years, as it avoids the use of ground truth data, and also because monocular cameras are readily available in most autonomous devices. Although some effective monocular depth estimation networks have been reported previously, such as Monodepth2 and SC-SfMLearner, most of these approaches are still computationally expensive for lightweight devices. Therefore, in this paper, we introduced a knowledge-distillation-based approach named LUMDE, to deal with the pixel-by-pixel unsupervised monocular depth estimation task. Specifically, we use a teacher network and lightweight student network to distill the depth information, and further, integrate a pose network into the student module to improve the depth performance. Moreover, referring to the idea of the Generative Adversarial Network (GAN), the outputs of the student network and teacher network are taken as fake and real samples, respectively, and Transformer is introduced as the discriminator of GAN to further improve the depth prediction results. The proposed LUMDE method achieves state-of-the-art (SOTA) results in the knowledge distillation of unsupervised depth estimation and also outperforms the results of some dense networks. The proposed LUMDE model only loses 2.6% on δ1 accuracy on the NYUD-V2 dataset compared with the teacher network but reduces the computational complexity by 95.2%.

PRAGAN: Progressive Recurrent Attention GAN with Pretrained ViT Discriminator for Single-Image Deraining

Images captured in bad weather are not conducive to visual tasks. Rain streaks in rainy images will significantly affect the regular operation of imaging equipment; to solve this problem, using multiple neural networks is a trend. The ingenious integration of network structures allows for full use of the powerful representation and fitting abilities of deep learning to complete low-level visual tasks. In this study, we propose a generative adversarial network (GAN) with multiple attention mechanisms for image rain removal tasks. Firstly, to the best of our knowledge, we propose a pretrained vision transformer (ViT) as the discriminator in GAN for single-image rain removal for the first time. Secondly, we propose a neural network training method that can use a small amount of data for training while maintaining promising results and reliable visual quality. A large number of experiments prove the correctness and effectiveness of our method. Our proposed method achieves better results on synthetic and real image datasets than multiple state-of-the-art methods, even when using less training data.

Resnet Features and Optimization Enabled Deep Learning for Indoor Object Detection and Object Recognition

Indoor object detection and recognition (IODR) helps to progress the quality life of the visually weakened person by helping them in indoor navigation along with their day-to-day activities. This research introduced the African Adam Optimization-based SqueezeNet (AAO-based SqueezeNet) for object detection and recognition. Moreover, Generative Adversarial Network (GAN) is exploited to detect the thing in the images with the assistance of a generator and discriminator in GAN. The features, such as texture and Resnet features are extracted in the detected objects. In addition, the objects are recognized using SqueezeNet based on the extracted features. Moreover, the training process of SqueezeNet is done using devised AAO algorithm, which is the concatenation of the African Vultures Optimization Algorithm (AVOA) and Adam optimizer (AO). Analysis is done based on the metrics, such as testing accuracy, precision, and recall using the Mendeley dataset and it accomplished the values of 0.905, 0.902, and 0.939, respectively.

PSGAN: Revisit the binary discriminator and an alternative for face frontalization

Generative adversarial network (GAN) based face frontalization is a cheap and convenient way to eliminate the impact of pose variance on face recognition. The sigmoid cross-entropy loss function is usually employed for the discriminator in those GAN based face synthesis methods. There are two disadvantages for this loss function: 1) The discriminator always wins the generator easily at the beginning of training because the convergence of the discriminator and the generator is unbalanced; 2) The training of GANs becomes unstable due to the prediction boundary uncertainty and massive parameters of the traditional binary discriminator. In order to eliminate the impacts caused by the traditional discriminator in the general GANs, a Bayesian induced perceptual self-representation discriminator (i.e.PSD) is proposed, which can also maintain the identity information, and simultaneously reduce the model parameters and training difficulty. There are three key contributions in this work: 1) On the basis of PSD, a perceptual self-representation GAN (i.e.PSGAN) with a new architecture is proposed, which reduces the training difficulty without lowering the synthetic quality; 2) In order to further improve the performance of our method, multiple features extracted from different layers are adopted to constitute a multi-perceptual self-representation discriminator (i.e.MPSD); 3) The proposed PSD discriminator is more lightweight with fewer parameters and can also be easily plugged and played in various GANs. Extensive qualitative and quantitative experiments on both restricted and unrestricted face databases and non-facial datasets demonstrate its superiority.

Exploiting Deep Generative Prior for Versatile Image Restoration and Manipulation.

Learning a good image prior is a long-term goal for image restoration and manipulation. While existing methods like deep image prior (DIP) capture low-level image statistics, there are still gaps toward an image prior that captures rich image semantics including color, spatial coherence, textures, and high-level concepts. This work presents an effective way to exploit the image prior captured by a generative adversarial network (GAN) trained on large-scale natural images. As shown in Fig. 1, the deep generative prior (DGP) provides compelling results to restore missing semantics, e.g., color, patch, resolution, of various degraded images. It also enables diverse image manipulation including random jittering, image morphing, and category transfer. Such highly flexible restoration and manipulation are made possible through relaxing the assumption of existing GAN inversion methods, which tend to fix the generator. Notably, we allow the generator to be fine-tuned on-the-fly in a progressive manner regularized by feature distance obtained by the discriminator in GAN. We show that these easy-to-implement and practical changes help preserve the reconstruction to remain in the manifold of nature images, and thus lead to more precise and faithful reconstruction for real images. Code is available at https://github.com/XingangPan/deep-generative-prior.

GAN-based semi-supervised learning method for identification of the faulty feeder in resonant grounding distribution networks

Accurate identification of the faulty feeder after a single-phase-to-ground fault in an arc suppression coil grounding distribution network remains a significant challenge. Recently, intelligent learning-based methods and especially deep learning methods have attracted much attention. To our knowledge, these methods usually assume that the training samples are sufficient. However, it is difficult to obtain abundant labeled samples in a practical environment. In this paper, we propose a semi-supervised learning model based on generative adversarial networks (GAN) to reliably identify the faulty feeder. The discriminator of GAN classifies the synthetic data which is generated by the generator into a new class. We revise the loss functions of the discriminator and generator, and the discriminator and generator play a maximum and minimum game. The proposed method can significantly improve the performance of faulty feeder identification when a small percentage of training samples are labeled. Various types of faults are simulated to consist of the training dataset and testing dataset. The simulation test results, sensitive analysis, comparing analysis, and recorded data obtained in a full-scale test field test demonstrate the higher performance of the proposed method.