Pairwise Comparison Network for Remote-Sensing Scene Classification
- 31 December 2021
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 19 (1545598X) , 1-5
Abstract
Remote-sensing scene classification aims to assign a specific semantic label to a remote-sensing image. Recently, convolutional neural networks (CNNs) have greatly improved the performance of remote-sensing scene classification. However, some confused images may be easily recognized as the incorrect category, which generally degrade the performance. The differences between image pairs can be used to distinguish image categories. This letter proposed a pairwise comparison network (PCNet), which contains two main steps: pairwise selection and pairwise representation. The proposed network first selects similar image pairs and then represents the image pairs with pairwise representations. The self-representation is introduced to highlight the informative parts of each image itself, while the mutual representation is proposed to capture the subtle differences between image pairs. Comprehensive experimental results on two challenging datasets (AID, NWPU-RESISC45) demonstrate the effectiveness of the proposed network.Keywords
All Related Versions
Funding Information
- National Science Fund for Distinguished Young Scholars (61925112)
- National Natural Science Foundation of China (61806193, 61772510)
- Innovation Capability Support Program of Shaanxi (2020KJXX-091, 2020TD-015)
This publication has 16 references indexed in Scilit:
- Error-Tolerant Deep Learning for Remote Sensing Image Scene ClassificationIEEE Transactions on Cybernetics, 2021
- Remote Sensing Image Scene Classification Based on an Enhanced Attention ModuleIEEE Geoscience and Remote Sensing Letters, 2020
- Automatic Weakly Supervised Object Detection From High Spatial Resolution Remote Sensing Images via Dynamic Curriculum LearningIEEE Transactions on Geoscience and Remote Sensing, 2020
- Mental Retrieval of Remote Sensing Images via Adversarial Sketch-Image Feature LearningIEEE Transactions on Geoscience and Remote Sensing, 2020
- Self-Attention-Based Deep Feature Fusion for Remote Sensing Scene ClassificationIEEE Geoscience and Remote Sensing Letters, 2020
- Marginal Center Loss for Deep Remote Sensing Image Scene ClassificationIEEE Geoscience and Remote Sensing Letters, 2019
- Remote Sensing Scene Classification by Gated Bidirectional NetworkIEEE Transactions on Geoscience and Remote Sensing, 2019
- Skip-Connected Covariance Network for Remote Sensing Scene ClassificationIEEE Transactions on Neural Networks and Learning Systems, 2019
- Siamese Convolutional Neural Networks for Remote Sensing Scene ClassificationIEEE Geoscience and Remote Sensing Letters, 2019
- A Deep Scene Representation for Aerial Scene ClassificationIEEE Transactions on Geoscience and Remote Sensing, 2019