mlsanityData to 7 Oct 2026

Quantum Down Sampling Filter for Variational Auto-encoder

arXiv 2501.06259 ↗First posted 9 Jan 2025cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

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 Fr'echet 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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 18 of its 43 references that are in the map. First posted on arXiv 9 Jan 2025.

Builds on

18 of 43 references.

References · 18

  1. 2019An Introduction to Variational Autoencoderscited by 997
  2. 2015Adversarial Autoencoderscited by 359
  3. 2019Parameterized quantum circuits as machine learning modelscited by 330
  4. 2019Diagnosing and Enhancing VAE Modelscited by 192
  5. 2018Quantum generative adversarial networkscited by 128
  6. 2020Experimental Quantum Generative Adversarial Networks for Image Generationcited by 83
  7. 2017Improved Variational Autoencoders for Text Modeling using Dilated Convolutionscited by 81
  8. 2023Quantum machine learning for image classificationcited by 56
  9. 2020Variational Autoencoders for Learning Nonlinear Dynamics of Physical Systemscited by 50
  10. 2018Quantum Variational Autoencodercited by 41
  11. 2023Complexity Matters: Rethinking the Latent Space for Generative Modelingcited by 19
  12. 2020Classification and reconstruction of optical quantum states with deep neural networkscited by 17
6 more
  1. 2017Learning hard quantum distributions with variational autoencoderscited by 16
  2. 2020Super-resolution Variational Auto-Encoderscited by 7
  3. 2020High-Dimensional Similarity Search with Quantum-Assisted Variational Autoencodercited by 5
  4. 2020Self-Supervised Variational Auto-Encoderscited by 5
  5. 2018Adversarial Training of Variational Auto-encoders for High Fidelity Image Generationcited by 3
  6. 2024Deep learning-based variational autoencoder for classification of quantum and classical states of lightcited by 1

Built on by

Not cited yet.