# HQViT: Hybrid Quantum Vision Transformer for Image Classification

arXiv: https://arxiv.org/abs/2504.02730 · HTML: https://mlsanity.com/paper/2504.02730/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 37 references that are in the map.
- First posted on arXiv 3 Apr 2025.

## Builds on (most cited first, 16 of 16)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Image Transformer](https://mlsanity.com/paper/1802.05751/) (2018)
- [Variational Quantum Algorithms](https://mlsanity.com/paper/2012.09265/) (2020)
- [MedMNIST v2 -- A large-scale lightweight benchmark for 2D and 3D biomedical image classification](https://mlsanity.com/paper/2110.14795/) (2021)
- [Supervised learning with quantum enhanced feature spaces](https://mlsanity.com/paper/1804.11326/) (2018)
- [A Survey on Visual Transformer](https://mlsanity.com/paper/2012.12556/) (2020)
- [Parameterized quantum circuits as machine learning models](https://mlsanity.com/paper/1906.07682/) (2019)
- [Transformer-Based Visual Segmentation: A Survey](https://mlsanity.com/paper/2304.09854/) (2023)
- [Quantum Long Short-Term Memory](https://mlsanity.com/paper/2009.01783/) (2020)
- [Recurrent Quantum Neural Networks](https://mlsanity.com/paper/2006.14619/) (2020)
- [Quantum Vision Transformers](https://mlsanity.com/paper/2209.08167/) (2022)
- [Quantum Self-Attention Neural Networks for Text Classification](https://mlsanity.com/paper/2205.05625/) (2022)
- [QSAN: A Near-term Achievable Quantum Self-Attention Network](https://mlsanity.com/paper/2207.07563/) (2022)
- [QKSAN: A Quantum Kernel Self-Attention Network](https://mlsanity.com/paper/2308.13422/) (2023)

## Built on by (most cited first, 7 of 7)

- [Quantum Graph Attention Network: A Novel Quantum Multi-Head Attention Mechanism for Graph Learning](https://mlsanity.com/paper/2508.17630/) (2025)
- [PGKET: A Photonic Gaussian Kernel Enhanced Transformer](https://mlsanity.com/paper/2507.19041/) (2025)
- [Quantum Phase Recognition via Quantum Attention Mechanism](https://mlsanity.com/paper/2602.00473/) (2026)
- [Magnitude Is All You Need? Rethinking Phase in Quantum Encoding of Complex SAR Data](https://mlsanity.com/paper/2604.14229/) (2026)
- [Effective Dimension Governs Generalization in Quantum Kernel Vision Models](https://mlsanity.com/paper/2606.20183/) (2026)
- [QiT: Quantum-Inspired Transformer for Visual Recognition Task](https://mlsanity.com/paper/2609.17789/) (2026)
- [QINA: Quantum-Inspired Nonlinear Adapters for Pretrained Vision Models](https://mlsanity.com/paper/2609.29592/) (2026)

## Abstract (arXiv)

Transformer-based architectures have revolutionized the landscape of deep learning. In computer vision domain, Vision Transformer demonstrates remarkable performance on par with or even surpassing that of convolutional neural networks. However, the quadratic computational complexity of its self-attention mechanism poses challenges for classical computing, making model training with high-dimensional input data, e.g., images, particularly expensive. To address such limitations, we propose a Hybrid Quantum Vision Transformer (HQViT), that leverages the principles of quantum computing to accelerate model training while enhancing model performance. HQViT introduces whole-image processing with amplitude encoding to better preserve global image information without additional positional encoding. By leveraging quantum computation on the most critical steps and selectively handling other components in a classical way, we lower the cost of quantum resources for HQViT. The qubit requirement is minimized to O(log2N) and the number of parameterized quantum gates is only O(log2d), making it well-suited for Noisy Intermediate-Scale Quantum devices. By offloading the computationally intensive attention coefficient matrix calculation to the quantum framework, HQViT reduces the classical computational load by O(T2d). Extensive experiments across various computer vision datasets demonstrate that HQViT outperforms existing models, achieving a maximum improvement of up to 10.9% (on the MNIST 10-classification task) over the state of the art. This work highlights the great potential to combine quantum and classical computing to cope with complex image classification tasks.