摘要
The scene classification of high spatial resolution (HSR) images is a challenging task in the remote sensing community. How to construct a discriminative representation of the HSR scene is a key step to improve classification performance. In this letter, we propose a novel feature extraction method termed multilayer feature fusion network (MF(2)Net) for scene classification. At first, the transferred VGGNet-16 model is employed as a feature extractor to acquire multilayer convolutional features. Then, several layers including pooling, transformation, and fusion layers are designed to process hierarchical features in four branches, and the prediction probability can be obtained for classification. Finally, the proposed model is optimized by fine-tuning techniques, where a novel data augmentation approach is explored to improve generalization ability. As a result, MF(2)Net effectively applies useful information from multilayers to improve the accuracy of scene classification. The experimental results on AID and NWPU-RESISC45 data sets exhibit that the MF(2)Net method obtains quite competitive classification results compared with many state-of-the-art methods.
学科与关键词
- M2FN: A Multilayer and Multiattention Fusion Network for Remote Sensing Image Scene ClassificationZheng, Hongyu; Song, Tiecheng*; Gao, Chenqiang; Guo, TanIEEE Geoscience and Remote Sensing Letters, 2022, 19: 6511805.被引 8
- MGML: Multigranularity Multilevel Feature Ensemble Network for Remote Sensing Scene ClassificationZhao, Qi; Lyu, Shuchang; Li, Yuewen; Ma, Yujing; Chen, Lijiang*IEEE Transactions on Neural Networks and Learning Systems, 2023, 34(5): 2308-2322.被引 31
- Mining Hierarchical Information of CNNs for Scene Classification of VHR Remote Sensing ImagesXu, Kejie; Deng, Peifang; Huang, Hong*IEEE Transactions on Big Data, 2023, 9(2): 542-554.被引 4
