Cycle-Consistent Adversarial Networks for Realistic Pervasive Change Generation in Remote Sensing Imagery
This provides a method for controlled evaluation of change detection algorithms in remote sensing, which is incremental as it applies an existing CycleGAN technique to a new domain.
The paper tackles the problem of generating realistic pervasive changes in remote sensing imagery to evaluate change detection algorithms, using a CycleGAN that requires low training data and demonstrates its application by creating snow-covered scenes from Sentinel-2 imagery for testing anomalous change detection.
This paper introduces a new method of generating realistic pervasive changes in the context of evaluating the effectiveness of change detection algorithms in controlled settings. The method, a cycle-consistent adversarial network (CycleGAN), requires low quantities of training data to generate realistic changes. Here we show an application of CycleGAN in creating realistic snow-covered scenes of multispectral Sentinel-2 imagery, and demonstrate how these images can be used as a test bed for anomalous change detection algorithms.