zxforchid/FSMINet

Code for GRSL 2022 paper. Fully Squeezed Multi-Scale Inference Network for Fast and Accurate Saliency Detection in Optical Remote Sensing Images.

FSMINet (GRSL 2022)

Kunye Shen, Xiaofei Zhou, Bin Wan, Ran Shi, Jiyong Zhang, 'Fully Squeezed Multi-Scale Inference Network for Fast and Accurate Saliency Detection in Optical Remote Sensing Images'.

Required libraries

Python 3.7
numpy 1.18.1
scikit-image 0.17.2
PyTorch 1.4.0
torchvision 0.5.0
glob

The SSIM loss is adapted from pytorch-ssim.

Usage

1. Clone this repo

https://github.com/Kunye-Shen/FSMINet.git

2. We provide the predicted saliency maps (GoogleDrive or baidu extraction code: 12so.). You can download directly through the above methods, or contact us through the following email.

zxforchid@outlook.com

Architecture

FSM Module

FSMINet

Quantitative Comparison

Qualitative Comparison

Citation

@article{shen2022fully,
  title={Fully Squeezed Multi-Scale Inference Network for Fast and Accurate Saliency Detection in Optical Remote Sensing Images},
  author={Shen, Kunye and Zhou, Xiaofei and Wan, Bin and Shi, Ran and Zhang, Jiyong},
  journal={IEEE Geoscience and Remote Sensing Letters},
  year={2022},
  publisher={IEEE}
}