Quantum Masked Autoencoders for Vision Learning

TL;DR

This paper introduces quantum masked autoencoders (QMAEs) that leverage quantum computing to improve feature learning and image reconstruction, outperforming existing quantum autoencoders in masked image tasks.

Contribution

The paper presents the first design and implementation of quantum masked autoencoders that learn missing features within quantum states, enhancing quantum autoencoder capabilities.

Findings

QMAEs can learn masked features of images effectively.

QMAEs outperform state-of-the-art quantum autoencoders by 12.86% in classification accuracy.

QMAEs reconstruct masked images with improved visual fidelity.

Abstract

Classical autoencoders are widely used to learn features of input data. To improve the feature learning, classical masked autoencoders extend classical autoencoders to learn the features of the original input sample in the presence of masked-out data. While quantum autoencoders exist, there is no design and implementation of quantum masked autoencoders that can leverage the benefits of quantum computing and quantum autoencoders. In this paper, we propose quantum masked autoencoders (QMAEs) that can effectively learn missing features of a data sample within quantum states instead of classical embeddings. We showcase that our QMAE architecture can learn the masked features of an image and can reconstruct the masked input image with improved visual fidelity in MNIST-family images. Experimental evaluation highlights that QMAE can significantly outperform (12.86% on average) in classification accuracy compared to state-of-the-art quantum autoencoders in the presence of masks.