This repository contains model checkpoints for the paper "A Change Detection Reality Check", Corley et al. published at the ICLR 2024 Machine Learning for Remote Sensing (ML4RS) Workshop
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.
- Downloads last month
- 0