Quantum Transfer Learning with Adversarial Robustness for Classification of High-Resolution Image Datasets
arXiv:2401.17009 · doi:10.1002/qute.202400268
Abstract
The application of quantum machine learning to large-scale high-resolution image datasets is not yet possible due to the limited number of qubits and relatively high level of noise in the current generation of quantum devices. In this work, we address this challenge by proposing a quantum transfer learning (QTL) architecture that integrates quantum variational circuits with a classical machine learning network pre-trained on ImageNet dataset. Through a systematic set of simulations over a variety of image datasets such as Ants & Bees, CIFAR-10, and Road Sign Detection, we demonstrate the superior performance of our QTL approach over classical and quantum machine learning without involving transfer learning. Furthermore, we evaluate the adversarial robustness of QTL architecture with and without adversarial training, confirming that our QTL method is adversarially robust against data manipulation attacks and outperforms classical methods.
References in corpus (24)
- FaceNet: A Unified Embedding for Face Recognition and Clustering
- Quantum Machine Learning
- Deep Learning for Anomaly Detection: A Review
- Quantum support vector machine for big data classification
- A Survey of Deep Learning Techniques for Autonomous Driving
- Quantum Convolutional Neural Networks
- Quantum principal component analysis
- Efficient Learning for Deep Quantum Neural Networks
- Challenges and Opportunities in Quantum Machine Learning
- Quantum advantage in learning from experiments
- Transfer learning in hybrid classical-quantum neural networks
- Quantum convolutional neural network for classical data classification
- Robust data encodings for quantum classifiers
- Hybrid Quantum-Classical Convolutional Neural Networks
- Quantum Adversarial Machine Learning
- Experimental quantum adversarial learning with programmable superconducting qubits
- Approximate amplitude encoding in shallow parameterized quantum circuits and its application to financial market indicator
- Benchmarking Adversarially Robust Quantum Machine Learning at Scale
- Classical-to-quantum convolutional neural network transfer learning
- Reflection Equivariant Quantum Neural Networks for Enhanced Image Classification
- Robust in Practice: Adversarial Attacks on Quantum Machine Learning
- Robustness Verification of Quantum Classifiers
- Noise robustness and experimental demonstration of a quantum generative adversarial network for continuous distributions
- A Deep Four-Stream Siamese Convolutional Neural Network with Joint Verification and Identification Loss for Person Re-detection