Unsupervised domain adaptation for the semantic segmentation of remote sensing images via one-shot image-to-image translation

Official URL: https://dx.doi.org/10.1109/LGRS.2023.3281458

Domain adaptation is one of the prominent strategies for handling both the scarcity of pixel-level ground truth and the domain shift, that is widely encountered in large-scale land use/cover map calculation. Studies focusing on adversarial domain adaptation via re-styling source domain samples, commonly through generative adversarial networks, have reported varying levels of success, yet they suffer from semantic inconsistencies, visual corruptions, and often require a large number of target domain samples. In this letter, we propose a new light-weight unsupervised domain adaptation method for the semantic segmentation of very high resolution remote sensing images, based on an image-to-image translation approach, via an encoder-decoder strategy where latent content representations are mixed across domains, and a perceptual network module and loss function enforce visual semantic consistency. We show through cross-domain comparative experiments that it i) leads to semantically consistent images, ii) can operate with a single target domain sample (i.e. one-shot), and iii) at a fraction of the number of parameters required from state-of-the-art methods, while still outperforming them. Code is available at github.com/Sarmadfismael/RSOS_I2I.