Comprehensive Evaluation of Deepfake Detection Models: Accuracy, Generalization, and Resilience to Adversarial Attacks by Maryam Abbasi, Paulo Váz, José Silva, Pedro Martins

“…Existing detection methods face challenges with generalization across datasets and vulnerability to adversarial attacks. …”
Get full text

Fault Recognition Method and Application Based on Generative Adversarial Network by Shuiliang Luo, Yongmei Huang, Yun Su, Shengkui Wang, Qianqian Liu, Yingqiang Qi, Fuhao Chang

“…ABSTRACT In view of the limitation of generalization ability faced by deep learning in fault identification, especially in the case of complex underground geological conditions and variable seismic data characteristics, it is often ineffective to directly use the network based on synthetic data training for fault prediction of real data. …”
Get full text

SpaGAN: A spatially-aware generative adversarial network for building generalization in image maps by Zhiyong Zhou, Cheng Fu, Robert Weibel

“…The progress of deep learning offers a new paradigm to overcome the coordination challenges faced by conventional building generalization algorithms. Some studies have confirmed the feasibility of several original semantic segmentation networks, such as U-Net and its variants and the conditional generative adversarial network (cGAN), for building generalization in image maps. …”
Get full text

Conditional Generative Adversarial Networks and Deep Learning Data Augmentation: A Multi-Perspective Data-Driven Survey Across Multiple Application Fields and Classification Archit... by Lucas C. Ribas, Wallace Casaca, Ricardo T. Fares

Get full text

A highly generalized federated learning algorithm for brain tumor segmentation by Jun Wen, Xiusheng Li, Xin Ye, Xiaoli Li, Hang Mao

Get full text

Data generation for asphalt pavement evaluation: Deep learning-based insights from generative models by Mohammad Sedighian-Fard, Amir Golroo, Mahdi Javanmardi, Alexandre Alahi, Mehdi Rasti

“…Using the Wasserstein Generative Adversarial Network with Gradient Penalty (WGAN-GP) to generate realistic pavement crack images, the U-Net segmentation model is optimized. …”
Get full text

Generative Adversarial Network for Real‐Time Flash Drought Monitoring: A Deep Learning Study by Ehsan Foroumandi, Keyhan Gavahi, Hamid Moradkhani

“…The developed architecture in this study employs a Markovian discriminator, which emphasizes the spatial dependencies, with a modified U‐Net generator, tuned for optimal performance. To determine the best loss function for the generator, four different networks are developed with different loss functions, including Mean Absolute Error (MAE), adversarial loss, a combination of adversarial loss with Mean Square Error (MSE), and a combination of adversarial loss with MAE. …”
Get full text

Deep Learning-Based Denoising for Optical Coherence Tomography: Evaluating Self-Supervised and Generative Models Across Retinal Datasets by Diogen BABUC, Alesia LOBONŢ, Alexandru FARCAŞ, Todor IVAŞCU, Sebastian-Aurelian ŞTEFĂNIGĂ

“…We aimed to evaluate the performance of five deep learning-based denoising models, namely Zero Shot Noise2Noise (ZS-N2N), DnCNN (for Gaussian denoising), U-Net Autoencoder, SwinIR Transformer, and CycleGAN. …”
Get full text

Cross-dataset evaluation of deep learning models for crack classification in structural surfaces by Rashid Taha, Mokji Musa Mohd, Rasheed Mohammed

“…This study investigates how well deep learning models generalize for crack classification across varied datasets and identifies which models perform best under self-testing and cross-testing conditions. …”
Get full text

Driver Drowsiness Detection Using Swin Transformer and Diffusion Models for Robust Image Denoising by Samy Abd El-Nabi, Ahmed F. Ibrahim, El-Sayed M. El-Rabaie, Osama F. Hassan, Naglaa F. Soliman, Khalil F. Ramadan, Walid El-Shafai

“…Moreover, a detailed sensitivity analysis of data augmentation strategies reveals that techniques such as rotation and horizontal flip substantially enhance the model’s generalization across variable visual inputs. The system also demonstrates improved robustness under real-world black-box scenarios and adversarial conditions. …”
Get full text

Generative Data Modelling for Diverse Populations in Africa: Insights from South Africa by Sally Sonia Simmons, John Elvis Hagan, Thomas Schack

“…Information missing from SAGE Wave 1, including demographic (e.g., race, age) and health (e.g., hypertension, blood pressure) indicators, were imputed using Generative Adversarial Imputation Nets (GAIN). CopulaGAN, CTGAN, and TVAE, sourced from the sdv 1.24.1 python library, generated 104,227 synthetic records based on the SAGE data constituents. …”
Get full text

Multi-Channel Speech Enhancement Using Labelled Random Finite Sets and a Neural Beamformer in Cocktail Party Scenario by Jayanta Datta, Ali Dehghan Firoozabadi, David Zabala-Blanco, Francisco R. Castillo-Soria

“…A neural network based on minimum variance distortionless response (MVDR) beamformer is considered as the beamformer of choice, where a residual dense convolutional graph-U-Net is applied in a generative adversarial network (GAN) setting to model the beamformer for target speech enhancement under reverberant conditions involving multiple moving speech sources. …”
Get full text

MA-DenseUNet: A Skin Lesion Segmentation Method Based on Multi-Scale Attention and Bidirectional LSTM by Wenbo Huang, Xudong Cai, Yang Yan, Yufeng Kang

“…Furthermore, it incorporates both channel and spatial attention mechanisms along with temporal modeling to improve boundary delineation and segmentation accuracy. A generative adversarial network (GAN) is also introduced to refine the segmentation output and boost generalization performance. …”
Get full text

Lightweight grape leaf disease recognition method based on transformer framework by Ning Zhang, Enxu Zhang, Guowei Qi, Fei Li, Cheng Lv

“…It provides a new method system with strong interpretability and excellent generalization performance for disease detection.…”
Get full text