English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Remote sensing change detection is crucial for understanding the dynamics ofour planet's surface, facilitating the monitoring of environmental changes,evaluating human impact, predicting future trends, and supportingdecision-making. In this work, we introduce a novel approach for changedetection that can leverage off-the-shelf, unlabeled remote sensing images inthe training process by pre-training a Denoising Diffusion Probabilistic Model(DDPM) - a class of generative models used in image synthesis. DDPMs learn thetraining data distribution by gradually converting training images into aGaussian distribution using a Markov chain. During inference (i.e., sampling),they can generate a diverse set of samples closer to the training distribution,starting from Gaussian noise, achieving state-of-the-art image synthesisresults. However, in this work, our focus is not on image synthesis but onutilizing it as a pre-trained feature extractor for the downstream applicationof change detection. Specifically, we fine-tune a lightweight change classifierutilizing the feature representations produced by the pre-trained DDPMalongside change labels. Experiments conducted on the LEVIR-CD, WHU-CD,DSIFN-CD, and CDD datasets demonstrate that the proposed DDPM-CD methodsignificantly outperforms the existing state-of-the-art change detectionmethods in terms of F1 score, IoU, and overall accuracy, highlighting thepivotal role of pre-trained DDPM as a feature extractor for downstreamapplications. We have made both the code and pre-trained models available athttps://github.com/wgcban/ddpm-cd

DDPM-CD: Denoising Diffusion Probabilistic Models as Feature Extractors for Change Detection