Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2501.06259 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909528412389376 |
|---|---|
| author | Riaz, Farina Zaman, Fakhar Suzuki, Hajime Abuadbba, Sharif Nguyen, David |
| author_facet | Riaz, Farina Zaman, Fakhar Suzuki, Hajime Abuadbba, Sharif Nguyen, David |
| contents | Variational autoencoders (VAEs) are fundamental for generative modeling and image reconstruction, yet their performance often struggles to maintain high fidelity in reconstructions. This study introduces a hybrid model, quantum variational autoencoder (Q-VAE), which integrates quantum encoding within the encoder while utilizing fully connected layers to extract meaningful representations. The decoder uses transposed convolution layers for up-sampling. The Q-VAE is evaluated against the classical VAE and the classical direct-passing VAE, which utilizes windowed pooling filters. Results on the MNIST and USPS datasets demonstrate that Q-VAE consistently outperforms classical approaches, achieving lower Fréchet inception distance scores, thereby indicating superior image fidelity and enhanced reconstruction quality. These findings highlight the potential of Q-VAE for high-quality synthetic data generation and improved image reconstruction in generative models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_06259 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Quantum Down Sampling Filter for Variational Auto-encoder Riaz, Farina Zaman, Fakhar Suzuki, Hajime Abuadbba, Sharif Nguyen, David Computer Vision and Pattern Recognition Variational autoencoders (VAEs) are fundamental for generative modeling and image reconstruction, yet their performance often struggles to maintain high fidelity in reconstructions. This study introduces a hybrid model, quantum variational autoencoder (Q-VAE), which integrates quantum encoding within the encoder while utilizing fully connected layers to extract meaningful representations. The decoder uses transposed convolution layers for up-sampling. The Q-VAE is evaluated against the classical VAE and the classical direct-passing VAE, which utilizes windowed pooling filters. Results on the MNIST and USPS datasets demonstrate that Q-VAE consistently outperforms classical approaches, achieving lower Fréchet inception distance scores, thereby indicating superior image fidelity and enhanced reconstruction quality. These findings highlight the potential of Q-VAE for high-quality synthetic data generation and improved image reconstruction in generative models. |
| title | Quantum Down Sampling Filter for Variational Auto-encoder |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2501.06259 |