Sahar Azadi

Sahar Azadi

Auto-generated profile, based on publicly available information

Sahar Azadi

Universidade do Minho

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
3 June 2021
Verified
Book Chapter
Closed access
PDF file
PFPedro Filipe Pires Faria
Pedro Filipe Pires Faria
SDSandra Manuela Gonçalves Dixe
Sandra Manuela Gonçalves Dixe
JLJoão Leite
João Leite
SASahar Azadi
Sahar Azadi
JMJosé Mendes
José Mendes
JBJoão Borges
João Borges

30 June 2025 in Computers and Informatics
Verified
Journal Article
Open access
PDF file
SASahar Azadi
Sahar Azadi
SDSandra Manuela Gonçalves Dixe
Sandra Manuela Gonçalves Dixe
JLJoao Leite
Joao Leite
JBJoão Borges
João Borges
Sandro QueirósSandro Queirós
Sandro Queirós
JFJaime Francisco Cruz Fonseca
Jaime Francisco Cruz Fonseca
Deep learning-based methodologies are a key component towards the goal of autonomous driving. For a successful application, these models require a significant amount of training data, which is difficult, time-consuming, and expensive to collect. This study assesses the effectiveness of Generative Adversarial Networks (GANs) in generating high-quality training images for in-vehicle applications using a limited dataset. Two advanced GAN architectures were compared for their ability to produce realistic in-vehicle RGB images. The results showed that the StyleGAN-ADA outperformed the MSG-GAN, generating images with better fidelity and accuracy, making it more suitable for scenarios with limited data. However, challenges such as mode collapse and long training times, particularly for high-resolution images, were identified. The models’ reliance on the quality and diversity of the training dataset also limits their effectiveness in real-world applications. This research highlights the potential of GANs to reduce the lack of data in autonomous driving, pointing to future approaches for optimizing these models.