Loading…

Context-Aware Guided Attention Based Cross-Feedback Dense Network for Hyperspectral Image Super-Resolution

Convolutional neural networks (CNNs) have shown impressive performance in computer vision due to their nonlinearity. Particularly, DenseNet (DN) that facilitates feature reuse in a feedforward (FF) manner has achieved state-of-the-art reconstruction accuracy for super-resolution (SR). However, most...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on geoscience and remote sensing 2022, Vol.60, p.1-14
Main Authors: Dong, Wenqian, Qu, Jiahui, Zhang, Tongzhen, Li, Yunsong, Du, Qian
Format: Article
Language:English
Subjects:
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Convolutional neural networks (CNNs) have shown impressive performance in computer vision due to their nonlinearity. Particularly, DenseNet (DN) that facilitates feature reuse in a feedforward (FF) manner has achieved state-of-the-art reconstruction accuracy for super-resolution (SR). However, most DN-based SR models transfer the features generated from each layer to all the subsequent layers, inevitably introducing redundancy, especially for high-dimensional hyperspectral (HS) images. To tackle this problem, we propose a two-branch cross-feedback dense network with context-aware guided attention (CFDcagaNet) for HS super-resolution (HSSR), which allows the network to learn the attention maps of high-level features and refine the low-level features in a feedback (FB) manner across two branches. Context-aware guided attention (CAGA) uses high-level posterior information to provide more faithful spatial-spectral guidance for low-level features, which enables CFDcagaNet to learn more effective spatial-spectral features at low levels and yield more effective spatial-spectral transfer in the network. Extensive experiments on widely used datasets demonstrate that the proposed method outperforms state-of-the-art methods in terms of both quantitative values and visual qualities.
ISSN:0196-2892
1558-0644
DOI:10.1109/TGRS.2022.3180484