Unsupervised Domain Adaptation for Semantic Segmentation using One-shot Image-to-Image Translation via Latent Representation Mixing

TL;DR

This paper introduces a novel one-shot unsupervised domain adaptation method for semantic segmentation of high-resolution images, using latent representation mixing and perceptual loss to achieve semantic consistency with fewer parameters.

Contribution

It proposes a new image-to-image translation approach that operates with a single target sample, ensuring semantic consistency and reducing model complexity.

Findings

Outperforms state-of-the-art domain adaptation methods in cross-city experiments.

Produces semantically consistent, noise-free images with minimal target data.

Requires fewer parameters than existing methods.

Abstract

Domain adaptation is one of the prominent strategies for handling both domain shift, that is widely encountered in large-scale land use/land cover map calculation, and the scarcity of pixel-level ground truth that is crucial for supervised semantic segmentation. 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 unsupervised domain adaptation method for the semantic segmentation of very high resolution images, that i) leads to semantically consistent and noise-free images, ii) operates 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. More specifically an image-to-image translation paradigm is proposed, based on an encoder-decoder principle where latent content representations are mixed across domains, and a perceptual network module and loss function is further introduced to enforce semantic consistency. Cross-city comparative experiments have shown that the proposed method outperforms state-of-the-art domain adaptation methods. Our source code will be available at \url{https://github.com/Sarmadfismael/LRM_I2I}.