Remote Sensing Image Scene Classification in Hybrid Classical–Quantum Transferring CNN with Small Samples
Sensors · 21.09.2023 · 23 (18) · 8010
DOI: 10.3390/s23188010 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 21.09.2023. Verfasst von Zhouwei Zhang und 8 weiteren Autor:innen. Beteiligte Einrichtung: Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China. Die Arbeit wurde bisher 26-mal zitiert (Crossref) und nennt 74 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the National Key R&D Program of China, the National Key R&D Program of China, the Major Project of High Resolution Earth Observation System.
Abstract (Originalsprache)
The scope of this research lies in the combination of pre-trained Convolutional Neural Networks (CNNs) and Quantum Convolutional Neural Networks (QCNN) in application to Remote Sensing Image Scene Classification(RSISC). Deep learning (RL) is improving by leaps and bounds pretrained CNNs in Remote Sensing Image (RSI) analysis, and pre-trained CNNs have shown remarkable performance in remote sensing image scene classification (RSISC). Nonetheless, CNNs training require massive, annotated data as samples. When labeled samples are not sufficient, the most common solution is using pre-trained CNNs with a great deal of natural image datasets (e.g., ImageNet). However, these pre-trained CNNs require a large quantity of labelled data for training, which is often not feasible in RSISC, especially when the target RSIs have different imaging mechanisms from RGB natural images. In this paper, we proposed an improved hybrid classical–quantum transfer learning CNNs composed of classical and quantum elements to classify open-source RSI dataset. The classical part of the model is made up of a ResNet network which extracts useful features from RSI datasets. To further refine the network performance, a tensor quantum circuit is subsequently employed by tuning parameters on near-term quantum processors. We tested our models on the open-source RSI dataset. In our comparative study, we have concluded that the hybrid classical–quantum transferring CNN has achieved better performance than other pre-trained CNNs based RSISC methods with small training samples. Moreover, it has been proven that the proposed algorithm improves the classification accuracy while greatly decreasing the amount of model parameters and the sum of training data.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China.
- National Engineering Laboratory for Satellite Remote Sensing Applications, Beijing 100094, China.
- School of Instrumentation and Optoelectronic Engineering, Beihang University, Beijing 100191, China.
ORCID-Profile: Xiaofei Mi, Xiangqin Wei, Yan Liu
Förderung
- the National Key R&D Program of China
- the National Key R&D Program of China
- the Major Project of High Resolution Earth Observation System
Zitieren
APA
Zhang, Z., Mi, X., Yang, J., Wei, X., Liu, Y., Yan, J., Liu, P., Gu, X., & Yu, T. (2023). Remote Sensing Image Scene Classification in Hybrid Classical–Quantum Transferring CNN with Small Samples. Sensors, 23(18), 8010. https://doi.org/10.3390/s23188010
Vancouver
Zhang Z, Mi X, Yang J, Wei X, Liu Y, Yan J, et al. Remote Sensing Image Scene Classification in Hybrid Classical–Quantum Transferring CNN with Small Samples. Sensors. 2023;23(18):8010. doi:10.3390/s23188010
BibTeX
@article{Zhang2023,
author = {Zhang, Zhouwei and Mi, Xiaofei and Yang, Jian and Wei, Xiangqin and Liu, Yan and Yan, Jian and Liu, Peizhuo and Gu, Xingfa and Yu, Tao},
title = {Remote Sensing Image Scene Classification in Hybrid Classical–Quantum Transferring CNN with Small Samples},
journal = {Sensors},
year = {2023},
volume = {23},
number = {18},
pages = {8010},
doi = {10.3390/s23188010}
}
EUVIMED