Pranav Durai*

Stanford Center for Innovation in In Vivo Imaging, Stanford University School of Medicine, Stanford, CA 94305, USA

*Corresponding Author: Pranav Durai, Stanford Center for Innovation in In Vivo Imaging, Stanford University School of Medicine, Stanford, CA 94305, USA.

Received: September 06, 2024; Published: December 13, 2024

Citation: Pranav Durai. “QuViT: Quantum Vision Transformer". Acta Scientific Computer Sciences 6.9 (2024):05-10.

Abstract

Image classification has traditionally relied on Convolutional Neural Networks (CNNs) for their ability to extract visual features, recognize and learn patterns. However, the emergence of Vision Transformers (ViTs) as an alternative approach, inspired by Trans formers in language tasks, brings the potential for capturing global image relationships and achieving competitive performance, interpretability, and scalability. The field of quantum computing has shown great promise, heralding a new era in computation and problem-solving. By harnessing the principles of quantum mechanics, quantum computers offer the potential to perform calculations at a scale and speed that surpass classical computers. This paper introduces QuViT, a quantum-accelerated vision transformer. With a novel q-input engine, q-encoder, and q-decoder, the proposed QuViT model follows a hybrid- approach that provides a promising avenue for building a quantum vision transformer that can handle yottabyte- scale image classification tasks with high accuracy, ef ficiency and paradigm shifting performance.

References

1. Feynman RP. “Simulating physics with computers”. International Journal of Theoretical Physics 21 (1982): 467-488.
2. Vaswani Ashish., et al. "Attention is all you need". Advances in Neural Information Processing Systems 30 (2017).
3. Dosovitskiy Alexey., et al. "An image is worth 16x16 words: Transformers for image recognition at scale". arXiv preprint arXiv:2010.11929 (2020).
4. Schuld Maria., et al. "An introduction to quantum machine learning". Contemporary Physics2 (2015): 172-185.
5. Cong Iris., et al. "Quantum convolutional neural networks". Nature Physics12 (2019): 1273-1278.
6. Fijany Amir and Colin P Williams. "Quantum wavelet transforms: Fast algorithms and complete circuits". Quantum Computing and Quantum Communications: First NASA International Conference, QCQC’98 Palm Springs, California, USA February 17–20, 1998 Selected Papers. Springer Berlin Heidelberg, (1999).
7. Farina Matteo., et al. "Quantum Multi-Model Fitting”. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. (2023).
8. Di Sipio Riccardo., et al. "The dawn of quantum natural language processing". ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, (2022).
9. Roy Pradosh K. “Quantum Fourier Transform” (2020).
10. Li Guangxi., et al. "Quantum self- attention neural networks for text classification". arXiv preprint arXiv:2205.05625 (2022).

Citation

Citation: Pranav Durai. “QuViT: Quantum Vision Transformer".Acta Scientific Computer Sciences 6.9 (2025): 05-10.

Copyright: © 2024 Pranav Durai. This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.