# A Domain Agnostic Normalization Layer for Unsupervised Adversarial Domain Adaptation

arXiv: https://arxiv.org/abs/1809.05298 · HTML: https://mlsanity.com/paper/1809.05298/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Sep 2018.

## Built on by (most cited first, 8 of 8)

- [Survey on Unsupervised Domain Adaptation for Semantic Segmentation for Visual Perception in Automated Driving](https://mlsanity.com/paper/2304.11928/) (2023)
- [Video Unsupervised Domain Adaptation with Deep Learning: A Comprehensive Survey](https://mlsanity.com/paper/2211.10412/) (2022)
- [Exploiting Image Translations via Ensemble Self-Supervised Learning for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2107.06235/) (2021)
- [Training Semantic Segmentation on Heterogeneous Datasets](https://mlsanity.com/paper/2301.07634/) (2023)
- [On Fine-Tuned Deep Features for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2210.14083/) (2022)
- [What is the Added Value of UDA in the VFM Era?](https://mlsanity.com/paper/2504.18190/) (2025)
- [Domain Adaptation and Active Learning for Fine-Grained Recognition in the Field of Biodiversity](https://mlsanity.com/paper/2110.11778/) (2021)
- [MIRANDA: MId-feature RANk-adversarial Domain Adaptation toward climate change-robust ecological forecasting with deep learning](https://mlsanity.com/paper/2604.00800/) (2026)

## Abstract (arXiv)

We propose a normalization layer for unsupervised domain adaption in semantic scene segmentation. Normalization layers are known to improve convergence and generalization and are part of many state-of-the-art fully-convolutional neural networks. We show that conventional normalization layers worsen the performance of current Unsupervised Adversarial Domain Adaption (UADA), which is a method to improve network performance on unlabeled datasets and the focus of our research. Therefore, we propose a novel Domain Agnostic Normalization layer and thereby unlock the benefits of normalization layers for unsupervised adversarial domain adaptation. In our evaluation, we adapt from the synthetic GTA5 data set to the real Cityscapes data set, a common benchmark experiment, and surpass the state-of-the-art. As our normalization layer is domain agnostic at test time, we furthermore demonstrate that UADA using Domain Agnostic Normalization improves performance on unseen domains, specifically on Apolloscape and Mapillary.