MEANet

This project provides the code and results for 'MEANet: An Effective and Lightweight Solution for Salient Object Detection in Optical Remote Sensing Images', ESWA, 2023. Link

Network Architecture

Requirements

python 3.7 + pytorch 1.9.0

Saliency maps

We provide saliency maps of our MEANet on ORSSD and EORSSD datasets and additional ORSI-4199 datasets.
We also provide saliency maps of our MEANet on DUT-O (code:MEAN), DUTS-TE (code:MEAN), HKU-IS (code:MEAN), ECSSD (code:MEAN), PASCALS (code:MEAN)

Training

Run train_MEANet.py.

Pre-trained model and testing

Download the following pre-trained model and put them in ./models/MEANet/, then run test_MEANet.py.
MEANet_EORSSD (code:lbc0)
MEANet_ORSSD (code:lbc1)
MEANet_ORSI-4199 (code:MEAN)
MEANet_DUTS-TR (code:MEAN)

Evaluation Tool

You can use the evaluation tool (MATLAB version) to evaluate the above saliency maps.

Acknowledgement

We would like to thank the contributors to the MCCNet.