Loading [MathJax]/jax/output/HTML-CSS/fonts/TeX/Script/Regular/Main.js
Low-Rank Nonlocal Representation for Remote Sensing Scene Classification | IEEE Journals & Magazine | IEEE Xplore

Low-Rank Nonlocal Representation for Remote Sensing Scene Classification


Abstract:

The nonlocal mechanism (NM) has shown its effectiveness in many real-world applications. However, it is usually criticized for its costly computation complexity in time a...Show More

Abstract:

The nonlocal mechanism (NM) has shown its effectiveness in many real-world applications. However, it is usually criticized for its costly computation complexity in time and space, which are both \mathscr {O}(H^{2}W^{2}) , where H\times W is the spatial dimension of input feature maps in height and width. In this letter, we first show that the NM can be expressed as a low-rank representation by theory. Then we propose a down-to-earth low-complexity global context acquisition mechanism, termed as the low-rank nonlocal representation (LNR), whose complexity in time and space are both approximatively \mathscr {O}(HW) . LNR is a general module that can be deployed on an arbitrary convolutional neural network (CNN) hierarchy for any visual recognition tasks. To demonstrate its superiority, experiments are carried out on four standard remote sensing scene classification benchmarks. Experimental results show that our proposed LNR can significantly reduce the computation cost by boosting the performance gain. Implementing LNR on the classical ResNet, in particular, can reduce at most 3.93 M model parameters.
Published in: IEEE Geoscience and Remote Sensing Letters ( Volume: 19)
Article Sequence Number: 8006905
Date of Publication: 25 January 2021

ISSN Information:

Funding Agency:


References

References is not available for this document.