# Unsupervised Domain Adaptation for Mobile Semantic Segmentation based on Cycle Consistency and Feature Alignment

arXiv: https://arxiv.org/abs/2001.04692 · HTML: https://mlsanity.com/paper/2001.04692/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Jan 2020.

## Built on by (most cited first, 29 of 29)

- [Learning Across Domains and Devices: Style-Driven Source-Free Domain Adaptation in Clustered Federated Learning](https://mlsanity.com/paper/2210.02326/) (2022)
- [One-shot Unsupervised Domain Adaptation with Personalized Diffusion Models](https://mlsanity.com/paper/2303.18080/) (2023)
- [Survey on Unsupervised Domain Adaptation for Semantic Segmentation for Visual Perception in Automated Driving](https://mlsanity.com/paper/2304.11928/) (2023)
- [CoMoGAN: continuous model-guided image-to-image translation](https://mlsanity.com/paper/2103.06879/) (2021)
- [Semantic Image Segmentation: Two Decades of Research](https://mlsanity.com/paper/2302.06378/) (2023)
- [Contrastive Learning and Self-Training for Unsupervised Domain Adaptation in Semantic Segmentation](https://mlsanity.com/paper/2105.02001/) (2021)
- [Unsupervised Domain Adaptation for Semantic Image Segmentation: a Comprehensive Survey](https://mlsanity.com/paper/2112.03241/) (2021)
- [Domain-Agnostic Prior for Transfer Semantic Segmentation](https://mlsanity.com/paper/2204.02684/) (2022)
- [Knowledge Distillation Methods for Efficient Unsupervised Adaptation Across Multiple Domains](https://mlsanity.com/paper/2101.07308/) (2021)
- [Contrast, Stylize and Adapt: Unsupervised Contrastive Learning Framework for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2306.09098/) (2023)
- [Latent Space Regularization for Unsupervised Domain Adaptation in Semantic Segmentation](https://mlsanity.com/paper/2104.02633/) (2021)
- [Towards Source-free Domain Adaptive Semantic Segmentation via Importance-aware and Prototype-contrast Learning](https://mlsanity.com/paper/2306.01598/) (2023)
- [Continual Coarse-to-Fine Domain Adaptation in Semantic Segmentation](https://mlsanity.com/paper/2201.06974/) (2022)
- [A-ACT: Action Anticipation through Cycle Transformations](https://mlsanity.com/paper/2204.00942/) (2022)
- [Road Scenes Segmentation Across Different Domains by Disentangling Latent Representations](https://mlsanity.com/paper/2108.03021/) (2021)
- [Focus on Your Target: A Dual Teacher-Student Framework for Domain-adaptive Semantic Segmentation](https://mlsanity.com/paper/2303.09083/) (2023)
- [Towards Unsupervised Domain Bridging via Image Degradation in Semantic Segmentation](https://mlsanity.com/paper/2412.10339/) (2024)
- [TridentAdapt: Learning Domain-invariance via Source-Target Confrontation and Self-induced Cross-domain Augmentation](https://mlsanity.com/paper/2111.15300/) (2021)
- [Cooperative Self-Training for Multi-Target Adaptive Semantic Segmentation](https://mlsanity.com/paper/2210.01578/) (2022)
- [Towards Robust Pseudo-Label Learning in Semantic Segmentation: An Encoding Perspective](https://mlsanity.com/paper/2512.06870/) (2025)
- [Balanced Learning for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2512.06886/) (2025)
- [Dual-level Interaction for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2307.07972/) (2023)
- [Weatherproofing Retrieval for Localization with Generative AI and Geometric Consistency](https://mlsanity.com/paper/2402.09237/) (2024)
- [DA-Cal: Towards Cross-Domain Calibration in Semantic Segmentation](https://mlsanity.com/paper/2602.20860/) (2026)
- [A Semantic Consistency Feature Alignment Object Detection Model Based on Mixed-Class Distribution Metrics](https://mlsanity.com/paper/2206.05765/) (2022)
- [Reducing Annotation Effort by Identifying and Labeling Contextually Diverse Classes for Semantic Segmentation Under Domain Shift](https://mlsanity.com/paper/2210.06749/) (2022)
- [Collaborative Learning for Enhanced Unsupervised Domain Adaptation](https://mlsanity.com/paper/2409.02699/) (2024)
- [FRIEREN: Federated Learning with Vision-Language Regularization for Segmentation](https://mlsanity.com/paper/2510.02114/) (2025)
- [Generative AI for Enhanced Wildfire Detection: Bridging the Synthetic-Real Domain Gap](https://mlsanity.com/paper/2511.16617/) (2025)

## Abstract (arXiv)

The supervised training of deep networks for semantic segmentation requires a huge amount of labeled real world data. To solve this issue, a commonly exploited workaround is to use synthetic data for training, but deep networks show a critical performance drop when analyzing data with slightly different statistical properties with respect to the training set. In this work, we propose a novel Unsupervised Domain Adaptation (UDA) strategy to address the domain shift issue between real world and synthetic representations. An adversarial model, based on the cycle consistency framework, performs the mapping between the synthetic and real domain. The data is then fed to a MobileNet-v2 architecture that performs the semantic segmentation task. An additional couple of discriminators, working at the feature level of the MobileNet-v2, allows to better align the features of the two domain distributions and to further improve the performance. Finally, the consistency of the semantic maps is exploited. After an initial supervised training on synthetic data, the whole UDA architecture is trained end-to-end considering all its components at once. Experimental results show how the proposed strategy is able to obtain impressive performance in adapting a segmentation network trained on synthetic data to real world scenarios. The usage of the lightweight MobileNet-v2 architecture allows its deployment on devices with limited computational resources as the ones employed in autonomous vehicles.