Abstract

In this paper, we propose a novel weighted shallow-deep feature fusion convolutional neural network (WSDFNet) for the task of multispectral image pansharpening. This network could effectively overcome the drawback of the common identity skip connection (ISC), and propagate shallow features scaled by a novel adaptive skip weighter (ASW) to deeper layers. By the technique, it could favor the feature fusion in different network depths adequately, as well as yield a promising outcome. Experimental results on reduced- and full-resolution WorldView-3 dataset demonstrate the superiority of the WSDFNet compared with recent state-of-the-art (SOTA) pansharpening approaches. Moreover, WSDFNet is also verified as a lightweight network.

Schematic Diagram of the Proposed Method

For details of Adaptive Skip Weighter (ASW), see below:

Downloads

Full paper: click here

PyTorch code: click here

Reference

@inproceedings{jin2021weighted,
  title={Weighted shallow-deep feature fusion network for pansharpening},
  author={Jin, Zi-Rong and Zhang, Tian-Jing and Jin, Cheng and Deng, Liang-Jian},
  booktitle={2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS},
  pages={2632--2635},
  year={2021},
  organization={IEEE}
}