# Adversarial Learning and Self-Teaching Techniques for Domain Adaptation in Semantic Segmentation

arXiv: https://arxiv.org/abs/1909.00781 · HTML: https://mlsanity.com/paper/1909.00781/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Sep 2019.

## Built on by (most cited first, 22 of 22)

- [Learning Across Domains and Devices: Style-Driven Source-Free Domain Adaptation in Clustered Federated Learning](https://mlsanity.com/paper/2210.02326/) (2022)
- [Survey on Unsupervised Domain Adaptation for Semantic Segmentation for Visual Perception in Automated Driving](https://mlsanity.com/paper/2304.11928/) (2023)
- [Balancing the Picture: Debiasing Vision-Language Datasets with Synthetic Contrast Sets](https://mlsanity.com/paper/2305.15407/) (2023)
- [SELMA: SEmantic Large-scale Multimodal Acquisitions in Variable Weather, Daytime and Viewpoints](https://mlsanity.com/paper/2204.09788/) (2022)
- [Unsupervised Continual Semantic Adaptation through Neural Rendering](https://mlsanity.com/paper/2211.13969/) (2022)
- [S3M-Net: Joint Learning of Semantic Segmentation and Stereo Matching for Autonomous Driving](https://mlsanity.com/paper/2401.11414/) (2024)
- [SAM4UDASS: When SAM Meets Unsupervised Domain Adaptive Semantic Segmentation in Intelligent Vehicles](https://mlsanity.com/paper/2401.08604/) (2023)
- [Semi-Supervised Semantic Segmentation Based on Pseudo-Labels: A Survey](https://mlsanity.com/paper/2403.01909/) (2024)
- [Latent Space Regularization for Unsupervised Domain Adaptation in Semantic Segmentation](https://mlsanity.com/paper/2104.02633/) (2021)
- [High-Resolution Synthetic RGB-D Datasets for Monocular Depth Estimation](https://mlsanity.com/paper/2305.01732/) (2023)
- [Towards Source-free Domain Adaptive Semantic Segmentation via Importance-aware and Prototype-contrast Learning](https://mlsanity.com/paper/2306.01598/) (2023)
- [Domain Adaptive Object Detection via Balancing Between Self-Training and Adversarial Learning](https://mlsanity.com/paper/2311.04815/) (2023)
- [Road Scenes Segmentation Across Different Domains by Disentangling Latent Representations](https://mlsanity.com/paper/2108.03021/) (2021)
- [ZoDi: Zero-Shot Domain Adaptation with Diffusion-Based Image Transfer](https://mlsanity.com/paper/2403.13652/) (2024)
- [When Cars meet Drones: Hyperbolic Federated Learning for Source-Free Domain Adaptation in Adverse Weather](https://mlsanity.com/paper/2403.13762/) (2024)
- [TiCoSS: Tightening the Coupling between Semantic Segmentation and Stereo Matching within A Joint Learning Framework](https://mlsanity.com/paper/2407.18038/) (2024)
- [Deep Transfer Learning for Kidney Cancer Diagnosis](https://mlsanity.com/paper/2408.04318/) (2024)
- [Unsupervised Domain Adaptation from Axial to Short-Axis Multi-Slice Cardiac MR Images by Incorporating Pretrained Task Networks](https://mlsanity.com/paper/2101.07653/) (2021)
- [Why You Should Try the Real Data for the Scene Text Recognition](https://mlsanity.com/paper/2107.13938/) (2021)
- [FlyAwareV2: A Multimodal Cross-Domain UAV Dataset for Urban Scene Understanding](https://mlsanity.com/paper/2510.13243/) (2025)
- [Industrial Synthetic Segment Pre-training](https://mlsanity.com/paper/2505.13099/) (2025)
- [FRIEREN: Federated Learning with Vision-Language Regularization for Segmentation](https://mlsanity.com/paper/2510.02114/) (2025)

## Abstract (arXiv)

Deep learning techniques have been widely used in autonomous driving systems for the semantic understanding of urban scenes. However, they need a huge amount of labeled data for training, which is difficult and expensive to acquire. A recently proposed workaround is to train deep networks using synthetic data, but the domain shift between real world and synthetic representations limits the performance. In this work, a novel Unsupervised Domain Adaptation (UDA) strategy is introduced to solve this issue. The proposed learning strategy is driven by three components: a standard supervised learning loss on labeled synthetic data; an adversarial learning module that exploits both labeled synthetic data and unlabeled real data; finally, a self-teaching strategy applied to unlabeled data. The last component exploits a region growing framework guided by the segmentation confidence. Furthermore, we weighted this component on the basis of the class frequencies to enhance the performance on less common classes. Experimental results prove the effectiveness of the proposed strategy in adapting a segmentation network trained on synthetic datasets, like GTA5 and SYNTHIA, to real world datasets like Cityscapes and Mapillary.