Quantum Down Sampling Filter for Variational Auto-encoder

2025-01-09

AI Summary

To address the blurring and structural detail loss inherent in classical variational autoencoders (VAEs) for 16×16 low-resolution image reconstruction, this paper proposes a quantum-enhanced VAE (Q-VAE). The method introduces a parameterized quantum circuit at the encoder to perform quantum-inspired downsampling filtering, followed by classical upsampling to 32×32; the decoder employs a lightweight CNN to preserve structural fidelity. This architecture represents the first integration of quantum computation with VAEs for super-resolution tasks, synergistically enhancing both feature preservation and generative quality. Experiments on MNIST and USPS demonstrate that Q-VAE achieves significantly lower Fréchet Inception Distance (FID) and mean squared error (MSE) compared to classical VAEs and CDP-VAE, confirming the substantive improvement conferred by quantum enhancement in reconstructing small-scale images.

Technology Category

• Machine Learning: Quantum Machine Learning
• Computer Vision: Generative Adversarial Networks (GANs) for Vision
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work

Abstract

Variational Autoencoders (VAEs) are essential tools in generative modeling and image reconstruction, with their performance heavily influenced by the encoder-decoder architecture. This study aims to improve the quality of reconstructed images by enhancing their resolution and preserving finer details, particularly when working with low-resolution inputs (16x16 pixels), where traditional VAEs often yield blurred or in-accurate results. To address this, we propose a hybrid model that combines quantum computing techniques in the VAE encoder with convolutional neural networks (CNNs) in the decoder. By upscaling the resolution from 16x16 to 32x32 during the encoding process, our approach evaluates how the model reconstructs images with enhanced resolution while maintaining key features and structures. This method tests the model's robustness in handling image reconstruction and its ability to preserve essential details despite training on lower-resolution data. We evaluate our proposed down sampling filter for Quantum VAE (Q-VAE) on the MNIST and USPS datasets and compare it with classical VAEs and a variant called Classical Direct Passing VAE (CDP-VAE), which uses windowing pooling filters in the encoding process. Performance is assessed using metrics such as the Fr'echet Inception Distance (FID) and Mean Squared Error (MSE), which measure the fidelity of reconstructed images. Our results demonstrate that the Q-VAE consistently outperforms both the Classical VAE and CDP-VAE, achieving significantly lower FID and MSE scores. Additionally, CDP-VAE yields better performance than C-VAE. These findings highlight the potential of quantum-enhanced VAEs to improve image reconstruction quality by enhancing resolution and preserving essential features, offering a promising direction for future applications in computer vision and synthetic data generation.

Problem

• Variational Autoencoders
• Image Reconstruction
• Small Image Size

Innovation

• Quantum Variational Autoencoder
• Quantum Subsampling Filter
• Image Reconstruction Quality