# Unsupervised Domain Adaptation with Multiple Domain Discriminators and Adaptive Self-Training

arXiv: https://arxiv.org/abs/2004.12724 · HTML: https://mlsanity.com/paper/2004.12724/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Apr 2020.

## Built on by (most cited first, 10 of 10)

- [Test-Time Training on Video Streams](https://mlsanity.com/paper/2307.05014/) (2023)
- [Survey on Unsupervised Domain Adaptation for Semantic Segmentation for Visual Perception in Automated Driving](https://mlsanity.com/paper/2304.11928/) (2023)
- [Unsupervised Continual Semantic Adaptation through Neural Rendering](https://mlsanity.com/paper/2211.13969/) (2022)
- [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)
- [Road Scenes Segmentation Across Different Domains by Disentangling Latent Representations](https://mlsanity.com/paper/2108.03021/) (2021)
- [An evaluation framework for synthetic data generation models](https://mlsanity.com/paper/2404.08866/) (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)
- [Action Recognition with Domain Invariant Features of Skeleton Image](https://mlsanity.com/paper/2111.11250/) (2021)
- [Robust Unsupervised Domain Adaptation for 3D Point Cloud Segmentation Under Source Adversarial Attacks](https://mlsanity.com/paper/2504.01659/) (2025)

## Abstract (arXiv)

Unsupervised Domain Adaptation (UDA) aims at improving the generalization capability of a model trained on a source domain to perform well on a target domain for which no labeled data is available. In this paper, we consider the semantic segmentation of urban scenes and we propose an approach to adapt a deep neural network trained on synthetic data to real scenes addressing the domain shift between the two different data distributions. We introduce a novel UDA framework where a standard supervised loss on labeled synthetic data is supported by an adversarial module and a self-training strategy aiming at aligning the two domain distributions. The adversarial module is driven by a couple of fully convolutional discriminators dealing with different domains: the first discriminates between ground truth and generated maps, while the second between segmentation maps coming from synthetic or real world data. The self-training module exploits the confidence estimated by the discriminators on unlabeled data to select the regions used to reinforce the learning process. Furthermore, the confidence is thresholded with an adaptive mechanism based on the per-class overall confidence. 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.