Quantum Masked Autoencoders for Vision Learning
This work addresses a gap in quantum machine learning for vision tasks, offering a novel quantum method that could enhance data reconstruction and classification in domains like image processing, though it appears incremental as an extension of existing quantum autoencoders.
The paper tackles the problem of learning missing features in data samples by proposing quantum masked autoencoders (QMAEs), which leverage quantum computing to improve feature learning over classical and quantum autoencoders, resulting in a 12.86% average increase in classification accuracy on MNIST images.
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 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.