当前位置: X-MOL 学术IEEE Geosci. Remote Sens. Lett. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Generative Adversarial Networks Under CutMix Transformations for Multimodal Change Detection
IEEE Geoscience and Remote Sensing Letters ( IF 4.8 ) Pub Date : 2022-08-23 , DOI: 10.1109/lgrs.2022.3201003
Anamaria Radoi

The current technological developments lead to increased heterogeneity and variability in remote sensing imagery. In this context, unsupervised multimodal change detection techniques are mandatory to perform a continuous monitoring and rapid damage assessment by means of heterogeneous remote sensing data. Taking advantage of the latest advances in deep learning, we address multimodal change detection from an intermodality image translation perspective. Intermodality translation is achieved by means of generative adversarial networks (GANs) built over U-Net architectures at both generator and discriminator levels and trained under CutMix transformations. A change prior is used to guide the learning process of the neural network framework and to reduce the impact of changed locations over the learned model. The change prior is derived in an unsupervised manner from comparisons between the postevent locations and $k$ nearest neighbor ( $k$ NN) locations determined in the preevent image. The experiments were conducted over several pairs of heterogeneous remote sensing images, and the comparisons with current state-of-the-art approaches show the effectiveness of the proposed multimodal change detection framework.

中文翻译:

用于多模态变化检测的 CutMix 变换下的生成对抗网络

当前的技术发展导致遥感图像的异质性和可变性增加。在这种情况下,无监督的多模态变化检测技术必须通过异构遥感数据进行连续监测和快速损害评估。利用深度学习的最新进展,我们从多模态图像翻译的角度解决多模态变化检测问题。多模态转换是通过在生成器和判别器级别的 U-Net 架构上构建的生成对抗网络 (GAN) 实现的,并在 CutMix 转换下进行训练。更改先验用于指导神经网络框架的学习过程,并减少更改位置对学习模型的影响。 $k$最近的邻居 ( $k$ NN) 在事件前图像中确定的位置。实验是在多对异构遥感图像上进行的,与当前最先进的方法的比较表明了所提出的多模态变化检测框架的有效性。
更新日期:2022-08-23
down
wechat
bug