University of Leicester
Browse
updated.pdf (1.03 MB)

Multi-level Feature Fusion Networks with Adaptive Channel Dimensionality Reduction for Remote Sensing Scene Classification

Download (1.03 MB)
journal contribution
posted on 2021-04-20, 11:34 authored by X Wang, L Duan, A Shi, Huiyu Zhou
Scene classification in very high-resolution (VHR) remote sensing (RS) images is a challenging task due to the complex and diverse content of the images. Recently, convolution neural networks (CNNs) have been utilized to tackle this task. However, CNNs cannot fully meet the needs of scene classification due to clutters and small objects in VHR images. To handle these challenges, this letter presents a novel multilevel feature fusion (MLFF) network with adaptive channel dimensionality reduction for RS scene classification. Specifically, an adaptive method is designed for channel dimensionality reduction of high-dimensional features. Then, an MLFF module is introduced to fuse the features in an efficient way. Experiments on three widely used data sets show that our model outperforms several state-of-the-art methods in terms of both accuracy and stability.

Funding

Fundamental Research Funds for the Central Universities; Six Talents Peak Project of Jiangsu Province; Jiangsu Province Government Scholarship for Studying Abroad; Royal Society-Newton Advanced Fellowship;

History

Author affiliation

School of Informatics

Version

  • AM (Accepted Manuscript)

Published in

IEEE Geoscience and Remote Sensing Letters

Publisher

Institute of Electrical and Electronics Engineers

issn

1545-598X

Acceptance date

2021-03-24

Copyright date

2021

Available date

2021-04-20

Language

en

Usage metrics

    University of Leicester Publications

    Categories

    No categories selected

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC