Object Detection Using Quantum Transfer Learning
Abstract
Object detection requires the joint learning of semantic identity and continuous spatial geometry. Existing quantum transfer learning approaches have focused mainly on classification tasks and do not support regression. Here, we introduce a physics informed hybrid classical-quantum architecture for object detection in which a pre-trained MobileNetV2 maps visual features into an eight qubits variationally quantum Hilbert space. The Hilbert space is partitioned into two task specific subspaces for semantic classification and geometric localization. Local quantum expectation values are used to predict continuous bounding box coordinates, while circuit topology regulates the flow of quantum information between the two tasks. We compare linear and circular CNOT topologies and show that periodic boundary conditions suppress bipartite entanglement without degrading detection performance. The circular architecture reaches a bipartite von Neumann entropy of 0.1688 bits and a Meyer-Wallach entanglement measure of 0.0370, while achieving an [email protected] of 0.9448 and an [email protected]:0.95 of 0.6558. A thermodynamic formulation further interprets the total learning loss as a variation in Helmholtz free energy. It interprets geometric localization as an effective internal energy contribution and semantic classification as an entropic contribution. These results indicate that high performance in the proposed object detection model does not require maximal entanglement. Instead, efficient learning can emerge through topology controlled information flow, targeted restriction of entanglement, and information renormalization within the Hilbert space.
Related
- Distinguishing Coherent Crosstalk from Calibration Drift via Pauli-Transfer Signatures and Quantum Edge Detection
- Cross‑device and cross‑modal arc detection: Transfer learning between EAST visible and WEST infrared diagnostics
- Towards Fair Benchmarking of Quantum Transfer Learning for Visual Classification
- Transfer learning-aided, artificial intelligence approach to evaluate optical properties of materials for classical and quantum photonic applications
- Generative Quantum Machine Learning Methods for Cancer Detection using Augmented Datasets
BibTeX
@misc{bahrami2026object,
title = {{Object Detection Using Quantum Transfer Learning}},
author = {Mohammad Bahrami and Morteza Rafiee and Mohsen Norouzi},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.15394},
eprint = {2609.15394},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.15394},
note = {CC0},
}
RIS
TY - UNPB
TI - Object Detection Using Quantum Transfer Learning
AU - Mohammad Bahrami
AU - Morteza Rafiee
AU - Mohsen Norouzi
PY - 2026
DA - 2026/09/14
PB - arXiv
DO - 10.48550/arxiv.2609.15394
UR - https://arxiv.org/abs/2609.15394
AB - Object detection requires the joint learning of semantic identity and continuous spatial geometry. Existing quantum transfer learning approaches have focused mainly on classification tasks and do not support regression. Here, we introduce a physics informed hybrid classical-quantum architecture for object detection in which a pre-trained MobileNetV2 maps visual features into an eight qubits variationally quantum Hilbert space. The Hilbert space is partitioned into two task specific subspaces for semantic classification and geometric localization. Local quantum expectation values are used to predict continuous bounding box coordinates, while circuit topology regulates the flow of quantum information between the two tasks. We compare linear and circular CNOT topologies and show that periodic boundary conditions suppress bipartite entanglement without degrading detection performance. The circular architecture reaches a bipartite von Neumann entropy of 0.1688 bits and a Meyer-Wallach entanglement measure of 0.0370, while achieving an [email protected] of 0.9448 and an [email protected]:0.95 of 0.6558. A thermodynamic formulation further interprets the total learning loss as a variation in Helmholtz free energy. It interprets geometric localization as an effective internal energy contribution and semantic classification as an entropic contribution. These results indicate that high performance in the proposed object detection model does not require maximal entanglement. Instead, efficient learning can emerge through topology controlled information flow, targeted restriction of entanglement, and information renormalization within the Hilbert space.
ER -