# Semantically Consistent Image-to-Image Translation for Unsupervised Domain Adaptation

Source: [Semantically Consistent Image-to-Image Translation for Unsupervised Domain Adaptation](<https://www.sota2.com/research/paper/68fa6b4f1e209131cea2d893>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T23:46:07.580Z

Authors: Stephan Brehm, Sebastian Scherer, Rainer Lienhart

Published: 2021-11-05T14:22:20.000Z

## Abstract

Unsupervised Domain Adaptation (UDA) aims to adapt models trained on a source domain to a new target domain where no labelled data is available. In this work, we investigate the problem of UDA from a synthetic computer-generated domain to a similar but real-world domain for learning semantic segmentation. We propose a semantically consistent image-to-image translation method in combination with a consistency regularisation method for UDA. We overcome previous limitations on transferring synthetic images to real looking images. We leverage pseudo-labels in order to learn a generative image-to-image translation model that receives additional feedback from semantic labels on both domains. Our method outperforms state-of-the-art methods that combine image-to-image translation and semi-supervised learning on relevant domain adaptation benchmarks, i.e., on GTA5 to Cityscapes and SYNTHIA to Cityscapes.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2111.03522>)

[PDF](<https://arxiv.org/pdf/2111.03522.pdf>)