Self-Supervised Representation Learning for Remote Sensing Image Change Detection Based on Temporal Prediction

By Huihui Dong, Wenping Ma, Yue Wu, Jun Zhang, L. Jiao. 2020

65 citations recorded by the source corpus.

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%.

Subfields: Atmospheric Science, Ecology, Media Technology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Atmospheric Science

In Ecology

In Media Technology

Citations in the corpus

Continual Barlow Twins: Continual Self-Supervised Learning for Remote Sensing Semantic Segmentation (2022, background): “Finally in [20], the authors propose a net that, imitating the discriminator of a generative adversarial network (GAN), identifies patches taken from two temporal images.”
MARE: Self-Supervised Multi-Attention REsu-Net for Semantic Segmentation in Remote Sensing (2021, methodology): “The only effort in the direction of SSL applied to RS is presented in [39].”
Self-Supervised Pretraining of Transformers for Satellite Image Time Series Classification (2020, methodology): “Dong et al. sampled image patches from bitemporal images and then used the temporal-source of these patches as pseudolabels for change detection [51].”
Self-Supervised Learning in Remote Sensing: A review (2022, background): “Change detection [93, 120, 151, 98, 230, 199, 215, 186, 186] is usually also a pixel-level task which utilizes multitemporal information to detect changing pixels.”
RingMo: A Remote Sensing Foundation Model With Masked Image Modeling (2023, background): “Dong et al. [50] leverage temporal prediction to deal with the change detection task.”
Self-Supervised Change Detection in Multiview Remote Sensing Images (2021, methodology): “Generative models [26]–[28] were adopted to generate features of bitemporal image pairs and detect the changes by an explicit comparison of the generated features.”