Aug 2026· Expert systems· Vol 43· 0 citations· 82 references
TL;DR
Various strategies and improvements to enhance GANs stability and performance are examined, including hybrid architectures that integrate GANs with other deep learning models and practical utility in domain‐specific expert systems.
Abstract
Generative adversarial networks (GANs) have fundamentally transformed the deep learning field since they enable the creation of synthetic data that closely matches real world data. This paper presents a comprehensive and up‐to‐date review of GANs variants and their revolutionary impact in several domains, and major developments in the new applications. We demonstrate the GANs architecture, versatility of GANs variants such as CycleGAN, bidirectional generative adversarial networks (BiGAN), quantum‐enhanced GAN (Q‐GAN) and StyleGAN. In this work, different GANs variants are analysed and combined with the proposed improvements that enhance stability and performance. Despite their outstanding performance, GANs suffer from instability and mode collapse during training. This paper examines various strategies and improvements to enhance GANs stability and performance, including hybrid architectures that integrate GANs with other deep learning models and practical utility in domain‐specific expert systems. Moreover, in the context of deepfakes, it considers the ethical and legal reflections of GANs generated content. We also contribute to a comprehensive perspective on current applications and future prospects of GANs, underscoring their versatility and promise in areas such as image synthesis, medical imaging, anomaly detection, code synthesis and urban simulation.
An in-depth and up- to-date overview of the GANs environment, principally highlighting the progress made over 2020 and beyond and proposing the idea of hybrid generative systems in the future while emphasizing the oppositional approach's extraordinary and enduring features.
Zahraa Salah Dhaif, Hind Jumaa Serteep· International Journal of Adv...· 0 citations
Generative Adversarial Networks (GANs) have become the backbone of data synthesis across multiple domains like healthcare, audio processing, real-time systems, and federated learning. Despite their revolutionary potential, GANs suffer from major challenges in stability, scalability, and data dependence. This seminar presents a critical and comparative review of ten research papers, each offering a unique solution to the core issues of GAN training instability. The reviewed methods encompass domain adaptation, feature distillation, theoretical regularization, adaptive augmentation, and hierarchical federated architectures. This report provides an in-depth literature analysis, followed by a cross-domain metric-wise performance comparison. The results indicate that no single method dominates across all scenarios, but hybrid combinations lead to the best generalizability and stability under constraints like limited data, non IID settings, or real-time computation. Findings are contextualized in terms of practical impact, with implications for the future design of robust, scalable GAN architectures.
C. Murali, R. Anand· International Journal For Mu...· 0 citations
This paper advocates for a forward-thinking approach that balances technical sophistication with human-centric principles, ensuring that adversarial deep learning evolves into a discipline not just of technical defense, but also of trust, transparency, and accountability.
Maisam Abbas, Ran-Zan Wang· IEEE Open Journal of the Com...· 0 citations
Automated surface defect detection in industrial manufacturing faces a critical challenge: the scarcity of balanced, annotated datasets severely limits the performance of deep learning models, particularly for minority defect classes that occur infrequently in production environments. While Generative Adversarial Networks (GANs) have emerged as promising tools for synthetic data generation, systematic comparative studies evaluating different GAN architectures and augmentation strategies for industrial defect detection remain limited. Furthermore, the integration of GAN-generated data with transfer learning techniques has not been thoroughly investigated. This study presents a comprehensive comparative analysis of four prominent GAN architectures, Deep Convolutional GAN (DCGAN), Conditional GAN (CGAN), Auxiliary Classifier GAN (ACGAN), and Wasserstein GAN with Gradient Penalty (WGAN-GP), applied to surface defect classification on a merged industrial dataset combining NEU-CLS and X-SSD (3,160 images across 13 defect classes). We systematically evaluate four augmentation strategies: uniform generation, selective minority oversampling, balanced augmentation, and distribution-aware generation. The generated synthetic images are integrated with transfer learning using a ResNet-50 backbone pretrained on ImageNet to assess downstream classification performance. Results show that GAN-based augmentation improves classification accuracy, particularly for minority defect types, however results depend strongly on the augmentation strategy. CGAN offered the best balance between accuracy, stability, and practical reliability. This work contributes by providing a benchmark for evaluating GAN-based augmentation methods in industrial inspection and by proposing a hybrid GAN–ResNet50 pipeline, which achieves superior classification accuracy through the integration of generative modeling with transfer learning.
Nour Dbouk, Majd Saied, Clovis Francis· Journal of Nondestructive Ev...· 0 citations
The study concluded that adversarial resilience is largely determined by the interaction between model architecture and defense strategy, highlighting the need for architecture-specific defense selection when developing secure medical image classification systems.
Y. Heryadi, I. Sonata, Bambang Krismono Triwijoyo· Matrik· 0 citations
One significant change to the product design lifecycle is the use of Generative AI to generate ideas for product designs based on Artificial Intelligence (AI). By enhancing human designers’ imaginative and analytical capacities, AI allows for the rapid development of fresh, optimal, and individually tailored ideas. In order to improve creativity and originality in cultural as well as creative product design, this research suggests a new AI-assisted design model that integrates Conditional Generative Adversarial Networks (C-GAN) and Deep Reinforcement Learning (DRL) and the Penguin Optimization Algorithm (POA). The approach simplifies the design process and greatly enhances design quality by integrating AI-driven decision help. Extensive trials validate the performance of the model, which is applied to four separate design tasks inside the study’s complete framework. Structured surveys as well as expert input are used to assess important criteria, such as practicality, cultural adaptation, and inventiveness. The Penguin Optimization Algorithm (POA) is a nature-inspired optimization technique based on the social behavior of penguins in search of food. It uses a population of candidate solutions, referred to as “penguins,” to explore the design space. The algorithm evaluates and refines the candidate solutions through a series of iterative steps, optimizing the design based on predefined criteria. The results show that compared to other methods, the C-GAN + DRL+ POA model is superior. Reduction of loss to 0.07, 93% model accuracy, 95% user satisfaction, and 0.92 Structural Similarity Index score are highlights. The results show that the model is the best at producing satisfying designs for users. Also, the model is quite efficient and has good generalizability, thus it may help with data and insights for cultural product design technologies.