Inception residual attention network for remote sensing image super-resolution

杨利霞

Inception residual attention network for remote sensingimage super-resolution

5 F. Y6 j! N3 E+ q, q& G* _How to enhance the spatial resolution for a remote sensing image is
- p3 a6 c* M, L0 zan important issue that we face. Many image super-resolution (SR)
; ]$ C$ c' M) q: [- ztechniques have been proposed for this purpose and deep con
1 o8 z* @) V# u7 X! l" }  fvolutional neural network (CNN) is the most effective approach in
recent 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
( ^) _! o( i" a" [paper, we propose a network named inception residual attention
network (IRAN) to address this problem. Specifically, we propose
: |% y* a% H0 U% @3 Q7 ]a spatial attention module to make the network adaptively learn
the importance of different spatial areas, so as to pay more atten
tion to the areas with high-frequency information. Furthermore, we
present an inception module to fuse local multilevel features, so as
* ^+ z7 q, X6 a. ^to provide richer information for reconstructing detailed textures. In
order to evaluate the effectiveness of the proposed method, a large
+ b& V& f/ s! \number of experiments are performed on UCMerced-LandUse data
set and the results show that the proposed method is superior to
# I) l! X' l7 P/ y. i4 Dthe current state-of-the-art methods in both visual effects and
& }8 g9 d' k, {3 ^8 iobjective indicators.

: `) \  g/ P$ [# M( ^

0 [, o9 D/ ~4 O
8 i0 {+ N% O5 K" R