Inception residual attention network for remote sensing image super-resolution

杨利霞

Inception residual attention network for remote sensingimage super-resolution

- j$ k0 B8 b! v4 Q- r
) ?! V! o% {# b6 T  Q0 j2 U
  K- h3 \6 V3 _4 \' Y9 RHow to enhance the spatial resolution for a remote sensing image is
; z3 J5 q, {: M# Yan important issue that we face. Many image super-resolution (SR)
5 a  O9 `" F2 h( \1 Y. Stechniques have been proposed for this purpose and deep con
4 m% M7 ~" z6 e* n+ x' Zvolutional neural network (CNN) is the most effective approach in
recent years. However, we observe that most CNN-based SR meth
) w$ e2 k  e& \# i6 Z4 a, m+ Oods treat low-frequency areas and high-frequency areas equally,
hence hindering the recovery of high-frequency information. In this
paper, we propose a network named inception residual attention
network (IRAN) to address this problem. Specifically, we propose
$ {1 L1 k) a- _" @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
to provide richer information for reconstructing detailed textures. In
( k) s! Y5 g7 |) B* B+ W$ ]/ G7 horder to evaluate the effectiveness of the proposed method, a large
  Y2 _0 M: O0 j( }0 ^number of experiments are performed on UCMerced-LandUse data
set and the results show that the proposed method is superior to
9 b6 \3 b. E; x; rthe current state-of-the-art methods in both visual effects and
objective indicators.


* J- @  N; d+ `) O) n  _! V  R