Unsupervised Change Detection Based on Image Reconstruction Loss

TL;DR

This paper introduces an unsupervised change detection method that uses image reconstruction loss on single images, enabling effective change detection without requiring labeled bi-temporal datasets.

Contribution

The novel approach detects changes using only unlabeled single images by training a reconstruction model, eliminating the need for labeled bi-temporal data.

Findings

Significant performance on multiple benchmark datasets

Effective change detection with only single images

Reconstruction loss highlights changed regions

Abstract

To train the change detector, bi-temporal images taken at different times in the same area are used. However, collecting labeled bi-temporal images is expensive and time consuming. To solve this problem, various unsupervised change detection methods have been proposed, but they still require unlabeled bi-temporal images. In this paper, we propose unsupervised change detection based on image reconstruction loss using only unlabeled single temporal single image. The image reconstruction model is trained to reconstruct the original source image by receiving the source image and the photometrically transformed source image as a pair. During inference, the model receives bi-temporal images as the input, and tries to reconstruct one of the inputs. The changed region between bi-temporal images shows high reconstruction loss. Our change detector showed significant performance in various change detection benchmark datasets even though only a single temporal single source image was used. The code and trained models will be publicly available for reproducibility.