Exploration of Metrics and Datasets to Assess the Fidelity of Images Generated by Generative Adversarial Networks
-
Published:2023-09-24
Issue:19
Volume:13
Page:10637
-
ISSN:2076-3417
-
Container-title:Applied Sciences
-
language:en
-
Short-container-title:Applied Sciences
Author:
Valdebenito Maturana Claudio Navar1ORCID, Sandoval Orozco Ana Lucila1ORCID, García Villalba Luis Javier1ORCID
Affiliation:
1. Group of Analysis, Security and Systems (GASS), Department of Software Engineering and Artificial Intelligence (DISIA), Faculty of Computer Science and Engineering, Office 431, Universidad Complutense de Madrid (UCM), Calle Profesor José García Santesmases 9, Ciudad Universitaria, 28040 Madrid, Spain
Abstract
Advancements in technology have improved human well-being but also enabled new avenues for criminal activities, including digital exploits like deep fakes, online fraud, and cyberbullying. Detecting and preventing such activities, especially for law enforcement agencies needing photo profiles for covert operations, is imperative. Yet, conventional methods relying on authentic images are hindered by data protection laws. To address this, alternatives like generative adversarial networks, stable diffusion, and pixel recurrent neural networks can generate synthetic images. However, evaluating synthetic image quality is complex due to the varied techniques. Metrics are crucial, offering objective measures to compare techniques and identify areas for enhancement. This article underscores metrics’ significance in evaluating synthetic images produced by generative adversarial networks. By analyzing metrics and datasets used, researchers can comprehend the strengths, weaknesses, and areas for further research on generative adversarial networks. The article ultimately enhances image generation precision and control by detailing dataset preprocessing and quality metrics for synthetic images.
Funder
European Commission
Subject
Fluid Flow and Transfer Processes,Computer Science Applications,Process Chemistry and Technology,General Engineering,Instrumentation,General Materials Science
Reference97 articles.
1. Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., and Bengio, Y. (2014). Generative Adversarial Nets. arXiv. 2. Van Den Oord, A., Kalchbrenner, N., and Kavukcuoglu, K. (2016, January 20–22). Pixel recurrent neural networks. Proceedings of the International Conference on Machine Learning, New York, NY, USA. 3. Rombach, R., Blattmann, A., Lorenz, D., Esser, P., and Ommer, B. (2022, January 18–24). High-Resolution Image Synthesis With Latent Diffusion Models. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA. 4. Karras, T., Aila, T., Laine, S., and Lehtinen, J. (May, January 30). Progressive Growing of GANs for Improved Quality, Stability, and Variation. Proceedings of the 6th International Conference on Learning Representations, ICLR 2018—Conference Track Proceedings, Vancouver, BC, Canada. 5. Kim, C.I., Kim, M., Jung, S., and Hwang, E. (2020). Simplified Fréchet Distance for Generative Adversarial Nets. Sensors, 20.
|
|