Quantum Vision Transformers

Abstract

In this work, quantum transformers are designed and analysed in detail by extending the state-of-the-art classical transformer neural network architectures known to be very performant in natural language processing and image analysis. Building upon the previous work, which uses parametrised quantum circuits for data loading and orthogonal neural layers, we introduce three types of quantum transformers for training and inference, including a quantum transformer based on compound matrices, which guarantees a theoretical advantage of the quantum attention mechanism compared to their classical counterpart both in terms of asymptotic run time and the number of model parameters. These quantum architectures can be built using shallow quantum circuits and produce qualitatively different classification models. The three proposed quantum attention layers vary on the spectrum between closely following the classical transformers and exhibiting more quantum characteristics. As building blocks of the quantum transformer, we propose a novel method for loading a matrix as quantum states as well as two new trainable quantum orthogonal layers adaptable to different levels of connectivity and quality of quantum computers. We performed extensive simulations of the quantum transformers on standard medical image datasets that showed competitively, and at times better performance compared to the classical benchmarks, including the best-in-class classical vision transformers. The quantum transformers we trained on these small-scale datasets require fewer parameters compared to standard classical benchmarks. Finally, we implemented our quantum transformers on superconducting quantum computers and obtained encouraging results for up to six qubit experiments.

20 pages

References in corpus (3)

• Beyond Barren Plateaus: Quantum Variational Algorithms Are Swamped With Traps
• Quantum Methods for Neural Networks and Application to Medical Image Classification
• Semiconductor Defect Detection by Hybrid Classical-Quantum Deep Learning

Cited by in corpus (16)

• Quantum Machine Learning for Digital Health? A Systematic Review
• Quantum Machine Learning in Drug Discovery: Applications in Academia and Pharmaceutical Industries
• Investigating the Quality of DermaMNIST and Fitzpatrick17k Dermatological Image Datasets
• Quantum Generative Learning for High-Resolution Medical Image Generation
• Trainability and Expressivity of Hamming-Weight Preserving Quantum Circuits for Machine Learning
• Quantum Vision Transformers for Quark-Gluon Classification
• Quantum autoencoders for image classification
• Why business adoption of quantum and AI technology must be ethical
• A Comparison Between Invariant and Equivariant Classical and Quantum Graph Neural Networks
• Quantum encoder for fixed Hamming-weight subspaces
• In Search of Extraterrestrial Artificial Intelligence Through Dyson Sphere-like structures around Primordial Black Holes
• Introduction to Quantum Error Correction with Stabilizer Codes
• Efficient Sparse State Preparation via Quantum Walks
• Quantum Phase Recognition via Quantum Attention Mechanism
• Double-bracket quantum algorithms for high-fidelity ground state preparation
• Quantum-Inspired Weight-Constrained Neural Network: Reducing Variable Numbers by 100x Compared to Standard Neural Networks