---
license: apache-2.0
---

This repository contains model checkpoints for the paper ["A Change Detection Reality Check", Corley et al.](https://arxiv.org/abs/2402.06994) published at the [ICLR 2024 Machine Learning for Remote Sensing (ML4RS) Workshop](https://ml-for-rs.github.io/iclr2024/)


### Abstract

In recent years, there has been an explosion of proposed change detection deep learning architectures in the remote sensing literature. These approaches claim to offer state-of the-artperformance on different standard benchmark datasets. However, has the field truly made significant progress? In this paper we perform experiments which conclude a simple U-Net segmentation baseline without training tricks or complicated architectural changes is still a top performer for the task of change detection.

### Code
The repository for model loading and experiments are provided in [here](https://github.com/isaaccorley/a-change-detection-reality-check).