Quantum self-supervised learning

The resurgence of self-supervised learning, whereby a deep learning model generates its own supervisory signal from the data, promises a scalable way to tackle the dramatically increasing size of real-world data sets without human annotation. However, the staggering computational complexity of these methods is such that for state-of-the-art performance, classical hardware requirements represent a significant bottleneck to further progress. Here we take the first steps to understanding whether quantum neural networks (QNNs) could meet the demand for more powerful architectures and test its effectiveness in proof-of-principle hybrid experiments. Interestingly, we observe a numerical advantage for the learning of visual representations using small-scale QNN over equivalently structured classical networks, even when the quantum circuits are sampled with only 100 shots. Furthermore, we apply our best quantum model to classify unseen images on the ibmq_paris quantum computer and find that current noisy devices can already achieve equal accuracy to the equivalent classical model on downstream tasks.

Automated summary

The resurgence of self-supervised learning offers a scalable solution for handling large datasets without human annotation. This study explores the potential of quantum neural networks (QNNs) in addressing hardware limitations and providing more powerful architectures, demonstrating the advantages of small-scale QNN in visual representation learning and the comparable accuracy of current noisy devices to classical models for image classification on downstream tasks.