SemI2I: Semantically Consistent Image-to-Image Translation for Domain Adaptation of Remote Sensing Data
This addresses domain adaptation for remote sensing data, which is an incremental improvement over existing methods.
The paper tackles domain shift in remote sensing image segmentation by proposing a data augmentation approach using GANs to transfer test data style to training data, and reports that their framework outperforms existing domain adaptation methods.
Although convolutional neural networks have been proven to be an effective tool to generate high quality maps from remote sensing images, their performance significantly deteriorates when there exists a large domain shift between training and test data. To address this issue, we propose a new data augmentation approach that transfers the style of test data to training data using generative adversarial networks. Our semantic segmentation framework consists in first training a U-net from the real training data and then fine-tuning it on the test stylized fake training data generated by the proposed approach. Our experimental results prove that our framework outperforms the existing domain adaptation methods.