Inception residual attention network for remote sensing image super-resolution

杨利霞

Inception residual attention network for remote sensingimage super-resolution

3 v; m6 j8 A* T1 m! h8 N- V# {

How to enhance the spatial resolution for a remote sensing image is
an important issue that we face. Many image super-resolution (SR)
techniques have been proposed for this purpose and deep con
volutional neural network (CNN) is the most effective approach in
0 J" d, X/ k2 k; X8 f) F7 T# Orecent years. However, we observe that most CNN-based SR meth
ods treat low-frequency areas and high-frequency areas equally,
hence hindering the recovery of high-frequency information. In this
! Q9 t+ X4 \# U3 f7 H) h( ~6 wpaper, we propose a network named inception residual attention
network (IRAN) to address this problem. Specifically, we propose
a spatial attention module to make the network adaptively learn
( _* a0 M; b" q' T: M7 rthe importance of different spatial areas, so as to pay more atten
3 e. I4 t: l1 Xtion to the areas with high-frequency information. Furthermore, we
present an inception module to fuse local multilevel features, so as
; X/ k  m( G6 S$ Lto provide richer information for reconstructing detailed textures. In
order to evaluate the effectiveness of the proposed method, a large
% Q  z1 a, \2 W* d9 nnumber of experiments are performed on UCMerced-LandUse data
. _# h; y- m3 C/ B; `set and the results show that the proposed method is superior to
the current state-of-the-art methods in both visual effects and
objective indicators.

' s+ e4 j8 w& f( N7 q8 g( W8 z


$ a  m- h$ m" o+ M