Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2507.09706 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911585511931904 |
|---|---|
| author | Al-Othni, Asma Al-Kuwari, Saif Fatmehsari, Mohammad Mahdi Nasiri Zaman, Kamila Ardeshir-Larijani, Ebrahim |
| author_facet | Al-Othni, Asma Al-Kuwari, Saif Fatmehsari, Mohammad Mahdi Nasiri Zaman, Kamila Ardeshir-Larijani, Ebrahim |
| contents | Generative Adversarial Networks (GANs) have demonstrated immense potential in synthesizing diverse and high-fidelity images. However, critical questions remain unanswered regarding how quantum principles might best enhance their representational and computational capacity. In this paper, we investigate hybrid quantum-classical GAN architectures supplemented by transfer learning to systematically examine whether incorporating Variational Quantum Circuits (VQCs) into the generator, the discriminator, or both improves performance over a fully classical baseline. Our findings indicate that fully hybrid models, which incorporate VQCs in both the generator and the discriminator, produce images with higher quality and achieve more favorable quantitative metrics compared to their fully classical counterparts. In particular, placing the quantum block in the generator appears to accelerate the early emergence of visual structure, whereas placing it in the discriminator slows early visual convergence but improves the final quantitative quality metric. Incorporating quantum blocks into both networks yields the strongest overall performance. Moreover, the model sustains comparable performance even when the dataset size is reduced. Overall, the results underscore that carefully integrating quantum computing with classical adversarial training and pretrained feature extraction can enrich GAN-based image synthesis. These insights open avenues for future work on higher-resolution tasks, alternative quantum circuit designs, and experimentation with emerging quantum hardware. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_09706 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Hybrid Quantum-Classical Generative Adversarial Networks with Transfer Learning Al-Othni, Asma Al-Kuwari, Saif Fatmehsari, Mohammad Mahdi Nasiri Zaman, Kamila Ardeshir-Larijani, Ebrahim Quantum Physics Generative Adversarial Networks (GANs) have demonstrated immense potential in synthesizing diverse and high-fidelity images. However, critical questions remain unanswered regarding how quantum principles might best enhance their representational and computational capacity. In this paper, we investigate hybrid quantum-classical GAN architectures supplemented by transfer learning to systematically examine whether incorporating Variational Quantum Circuits (VQCs) into the generator, the discriminator, or both improves performance over a fully classical baseline. Our findings indicate that fully hybrid models, which incorporate VQCs in both the generator and the discriminator, produce images with higher quality and achieve more favorable quantitative metrics compared to their fully classical counterparts. In particular, placing the quantum block in the generator appears to accelerate the early emergence of visual structure, whereas placing it in the discriminator slows early visual convergence but improves the final quantitative quality metric. Incorporating quantum blocks into both networks yields the strongest overall performance. Moreover, the model sustains comparable performance even when the dataset size is reduced. Overall, the results underscore that carefully integrating quantum computing with classical adversarial training and pretrained feature extraction can enrich GAN-based image synthesis. These insights open avenues for future work on higher-resolution tasks, alternative quantum circuit designs, and experimentation with emerging quantum hardware. |
| title | Hybrid Quantum-Classical Generative Adversarial Networks with Transfer Learning |
| topic | Quantum Physics |
| url | https://arxiv.org/abs/2507.09706 |