README.md

S²-cGAN: Self-Supervised Adversarial Representation Learning for Binary Change Detection in Multispectral Images

This repository contains the code of the paper S²-cGAN: Self-Supervised Adversarial Representation Learning for Binary Change Detection in Multispectral Images accepted at the IEEE International Geoscience and Remote Sensing Symposium, 2020. This work has been done at the Remote Sensing Image Analysis group by Jose Luis Holgado, Mahdyar Ravanbakhsh and Begüm Demir.

Abstract

Deep Neural Networks have recently demonstrated promising performance in binary change detection (CD) problems in remote sensing (RS), requiring a large amount of labeled multitemporal training samples. Since collecting such data is time-consuming and costly, most of the existing methods rely on pre-trained networks on publicly available computer vision (CV) datasets. However, because of the differences in image characteristics in CV and RS, this approach limits the performance of the existing CD methods. To address this problem, we propose a self-supervised conditional Generative Adversarial Network (S²-cGAN). The proposed S²-cGAN is trained to generate only the distribution of unchanged samples. To this end, the proposed method consists of two main steps: 1) Generating a reconstructed version of the input image as an unchanged image 2) Learning the distribution of unchanged samples through an adversarial game. Unlike the existing GAN based methods (which only use the discriminator during the adversarial training to supervise the generator), the S²-cGAN directly exploits the discriminator likelihood to solve the binary CD task. Experimental results show the effectiveness of the proposed S²-cGAN when compared to the state of the art CD methods.

If you use our code, please cite the associated paper as:

J. L. Holgado Alvarez, M. Ravanbakhsh, B. Demіr, "S²-cGAN: Self-Supervised Adversarial Representation Learning for Binary Change Detection in Multispectral Images", IEEE International Geoscience and Remote Sensing Symposium, Hawaii, USA, 2020.

@article{IG203936,
  author={J.L. {Holgado Alvarez}, M. {Ravanbakhsh} and B. {Demіr}},
  journal={IGARSS 2020 - 2020 IEEE International Geoscience and Remote Sensing Symposium}, 
  title={S^2-cGAN: Self-Supervised Adversarial Representation Learning for Binary Change Detection in Multispectral Images}, 
  year={2020}
}

S²-cGAN Change Detection Strategy

The following illustration represents the change detection strategy introduced in S²-cGAN.

Examples of score maps associated to a pair of patches, and its comparison to the ground-truth.

For the details please check our paper.

Setup

Prerequisites

• The code is tested with Python 3.7, PyTorch 0.4.1 and Ubuntu 18.04.
• Please, check out the requirements file for more information.
• For reproducibility, you can find our train and test sets here (password: Igarss_2020).

Hardware setup

The model was trained and tested in a machine with the following features:

• Nvidia Quadro P2000
• 16 GB RAM
• 12 CPU cores

Dataset

We used Worldview 2 satellite Very High Spatial Resolution (VHR) multispectral images dataset provided here.