Self-supervised representation learning for remote sensing image change detection based on temporal prediction

60Citations
Citations of this article
54Readers
Mendeley users who have this article in their library.

Abstract

Traditional change detection (CD) methods operate in the simple image domain or hand-crafted features, which has less robustness to the inconsistencies (e.g., brightness and noise distribution, etc.) between bitemporal satellite images. Recently, deep learning techniques have reported compelling performance on robust feature learning. However, generating accurate semantic supervision that reveals real change information in satellite images still remains challenging, especially for manual annotation. To solve this problem, we propose a novel self-supervised representation learning method based on temporal prediction for remote sensing image CD. The main idea of our algorithm is to transform two satellite images into more consistent feature representations through a self-supervised mechanism without semantic supervision and any additional computations. Based on the transformed feature representations, a better difference image (DI) can be obtained, which reduces the propagated error of DI on the final detection result. In the self-supervised mechanism, the network is asked to identify different sample patches between two temporal images, namely, temporal prediction. By designing the network for the temporal prediction task to imitate the discriminator of generative adversarial networks, the distribution-aware feature representations are automatically captured and the result with powerful robustness can be acquired. Experimental results on real remote sensing data sets show the effectiveness and superiority of our method, improving the detection precision up to 0.94-35.49%.

References Powered by Scopus

Reducing the dimensionality of data with neural networks

17221Citations
N/AReaders
Get full text

A fast learning algorithm for deep belief nets

13991Citations
N/AReaders
Get full text

Image-to-image translation with conditional adversarial networks

13559Citations
N/AReaders
Get full text

Cited by Powered by Scopus

RingMo: A Remote Sensing Foundation Model With Masked Image Modeling

167Citations
N/AReaders
Get full text

FCCDN: Feature constraint network for VHR image change detection

140Citations
N/AReaders
Get full text

Self-Supervised Pretraining of Transformers for Satellite Image Time Series Classification

129Citations
N/AReaders
Get full text

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Cite

CITATION STYLE

APA

Dong, H., Ma, W., Wu, Y., Zhang, J., & Jiao, L. (2020). Self-supervised representation learning for remote sensing image change detection based on temporal prediction. Remote Sensing, 12(11). https://doi.org/10.3390/rs12111868

Readers' Seniority

Tooltip

PhD / Post grad / Masters / Doc 27

79%

Researcher 7

21%

Readers' Discipline

Tooltip

Computer Science 15

50%

Engineering 9

30%

Agricultural and Biological Sciences 3

10%

Environmental Science 3

10%

Save time finding and organizing research with Mendeley

Sign up for free