# Unsupervised Domain Adaptation for Semantic Segmentation by Content Transfer

arXiv: https://arxiv.org/abs/2012.12545 · HTML: https://mlsanity.com/paper/2012.12545/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Dec 2020.

## Built on by (most cited first, 24 of 24)

- [Generalize then Adapt: Source-Free Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2108.11249/) (2021)
- [WildNet: Learning Domain Generalized Semantic Segmentation from the Wild](https://mlsanity.com/paper/2204.01446/) (2022)
- [Factors of Influence for Transfer Learning across Diverse Appearance Domains and Task Types](https://mlsanity.com/paper/2103.13318/) (2021)
- [DSP: Dual Soft-Paste for Unsupervised Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2107.09600/) (2021)
- [Prototypical Contrast Adaptation for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2207.06654/) (2022)
- [Survey on Unsupervised Domain Adaptation for Semantic Segmentation for Visual Perception in Automated Driving](https://mlsanity.com/paper/2304.11928/) (2023)
- [Domain-Specificity Inducing Transformers for Source-Free Domain Adaptation](https://mlsanity.com/paper/2308.14023/) (2023)
- [Personalized Image Semantic Segmentation](https://mlsanity.com/paper/2107.13978/) (2021)
- [GPS-GLASS: Learning Nighttime Semantic Segmentation Using Daytime Video and GPS data](https://mlsanity.com/paper/2207.13297/) (2022)
- [Threshold-adaptive Unsupervised Focal Loss for Domain Adaptation of Semantic Segmentation](https://mlsanity.com/paper/2208.10716/) (2022)
- [Hard-aware Instance Adaptive Self-training for Unsupervised Cross-domain Semantic Segmentation](https://mlsanity.com/paper/2302.06992/) (2023)
- [Unsupervised Modality Adaptation with Text-to-Image Diffusion Models for Semantic Segmentation](https://mlsanity.com/paper/2410.21708/) (2024)
- [Unsupervised Domain Adaptation for Semantic Segmentation via Low-level Edge Information Transfer](https://mlsanity.com/paper/2109.08912/) (2021)
- [Domain Adaptive Video Semantic Segmentation via Cross-Domain Moving Object Mixing](https://mlsanity.com/paper/2211.02307/) (2022)
- [Adaptive Texture Filtering for Single-Domain Generalized Segmentation](https://mlsanity.com/paper/2303.02943/) (2023)
- [DUDA: Distilled Unsupervised Domain Adaptation for Lightweight Semantic Segmentation](https://mlsanity.com/paper/2504.09814/) (2025)
- [Unsupervised Reinforcement Adaptation for Class-Imbalanced Text Classification](https://mlsanity.com/paper/2205.13139/) (2022)
- [UDA4Inst: Unsupervised Domain Adaptation for Instance Segmentation](https://mlsanity.com/paper/2405.09682/) (2024)
- [Domain Transformer: Predicting Samples of Unseen, Future Domains](https://mlsanity.com/paper/2106.06057/) (2021)
- [A Class-wise Non-salient Region Generalized Framework for Video Semantic Segmentation](https://mlsanity.com/paper/2212.14154/) (2022)
- [Repurposing SAM for User-Defined Semantics Aware Segmentation](https://mlsanity.com/paper/2312.02420/) (2023)
- [Vox-UDA: Voxel-wise Unsupervised Domain Adaptation for Cryo-Electron Subtomogram Segmentation with Denoised Pseudo Labeling](https://mlsanity.com/paper/2406.18610/) (2024)
- [Structured prototype regularization for synthetic-to-real driving scene parsing](https://mlsanity.com/paper/2603.16083/) (2026)
- [ForestSim: A Synthetic Benchmark for Intelligent Vehicle Perception in Unstructured Forest Environments](https://mlsanity.com/paper/2603.27923/) (2026)

## Abstract (arXiv)

In this paper, we tackle the unsupervised domain adaptation (UDA) for semantic segmentation, which aims to segment the unlabeled real data using labeled synthetic data. The main problem of UDA for semantic segmentation relies on reducing the domain gap between the real image and synthetic image. To solve this problem, we focused on separating information in an image into content and style. Here, only the content has cues for semantic segmentation, and the style makes the domain gap. Thus, precise separation of content and style in an image leads to effect as supervision of real data even when learning with synthetic data. To make the best of this effect, we propose a zero-style loss. Even though we perfectly extract content for semantic segmentation in the real domain, another main challenge, the class imbalance problem, still exists in UDA for semantic segmentation. We address this problem by transferring the contents of tail classes from synthetic to real domain. Experimental results show that the proposed method achieves the state-of-the-art performance in semantic segmentation on the major two UDA settings.