# Unsupervised BatchNorm Adaptation (UBNA): A Domain Adaptation Method for Semantic Segmentation Without Using Source Domain Representations

arXiv: https://arxiv.org/abs/2011.08502 · HTML: https://mlsanity.com/paper/2011.08502/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Nov 2020.

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

- [A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts](https://mlsanity.com/paper/2303.15361/) (2023)
- [FSDR: Frequency Space Domain Randomization for Domain Generalization](https://mlsanity.com/paper/2103.02370/) (2021)
- [Source-Free Unsupervised Domain Adaptation: A Survey](https://mlsanity.com/paper/2301.00265/) (2022)
- [Cross-View Regularization for Domain Adaptive Panoptic Segmentation](https://mlsanity.com/paper/2103.02584/) (2021)
- [Survey on Unsupervised Domain Adaptation for Semantic Segmentation for Visual Perception in Automated Driving](https://mlsanity.com/paper/2304.11928/) (2023)
- [Generalization by Adaptation: Diffusion-Based Domain Extension for Domain-Generalized Semantic Segmentation](https://mlsanity.com/paper/2312.01850/) (2023)
- [Strong but simple: A Baseline for Domain Generalized Dense Perception by CLIP-based Transfer Learning](https://mlsanity.com/paper/2312.02021/) (2023)
- [Online Domain Adaptation for Semantic Segmentation in Ever-Changing Conditions](https://mlsanity.com/paper/2207.10667/) (2022)
- [Simplifying Source-Free Domain Adaptation for Object Detection: Effective Self-Training Strategies and Performance Insights](https://mlsanity.com/paper/2407.07586/) (2024)
- [Continual BatchNorm Adaptation (CBNA) for Semantic Segmentation](https://mlsanity.com/paper/2203.01074/) (2022)
- [Active Source Free Domain Adaptation](https://mlsanity.com/paper/2205.10711/) (2022)
- [SALAD: Source-free Active Label-Agnostic Domain Adaptation for Classification, Segmentation and Detection](https://mlsanity.com/paper/2205.12840/) (2022)
- [Anatomy-guided domain adaptation for 3D in-bed human pose estimation](https://mlsanity.com/paper/2211.12193/) (2022)
- [Unseen Object Instance Segmentation with Fully Test-time RGB-D Embeddings Adaptation](https://mlsanity.com/paper/2204.09847/) (2022)
- [A Re-Parameterized Vision Transformer (ReVT) for Domain-Generalized Semantic Segmentation](https://mlsanity.com/paper/2308.13331/) (2023)
- [Exploiting Negative Learning for Implicit Pseudo Label Rectification in Source-Free Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2106.12123/) (2021)
- [AIF-SFDA: Autonomous Information Filter-driven Source-Free Domain Adaptation for Medical Image Segmentation](https://mlsanity.com/paper/2501.03074/) (2025)
- [Improving Online Performance Prediction for Semantic Segmentation](https://mlsanity.com/paper/2104.05255/) (2021)
- [On the Choice of Data for Efficient Training and Validation of End-to-End Driving Models](https://mlsanity.com/paper/2206.00608/) (2022)
- [On Fine-Tuned Deep Features for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2210.14083/) (2022)
- [Few-Shot Domain Adaptation for Learned Image Compression](https://mlsanity.com/paper/2409.11111/) (2024)
- [Enhancing AI Diagnostics: Autonomous Lesion Masking via Semi-Supervised Deep Learning](https://mlsanity.com/paper/2404.12450/) (2024)
- [Low-Resolution Face Recognition via Adaptable Instance-Relation Distillation](https://mlsanity.com/paper/2409.02049/) (2024)
- [SynthGenNet: a self-supervised approach for test-time generalization using synthetic multi-source domain mixing of street view images](https://mlsanity.com/paper/2509.02287/) (2025)

## Abstract (arXiv)

In this paper we present a solution to the task of "unsupervised domain adaptation (UDA) of a given pre-trained semantic segmentation model without relying on any source domain representations". Previous UDA approaches for semantic segmentation either employed simultaneous training of the model in the source and target domains, or they relied on an additional network, replaying source domain knowledge to the model during adaptation. In contrast, we present our novel Unsupervised BatchNorm Adaptation (UBNA) method, which adapts a given pre-trained model to an unseen target domain without using -- beyond the existing model parameters from pre-training -- any source domain representations (neither data, nor networks) and which can also be applied in an online setting or using just a few unlabeled images from the target domain in a few-shot manner. Specifically, we partially adapt the normalization layer statistics to the target domain using an exponentially decaying momentum factor, thereby mixing the statistics from both domains. By evaluation on standard UDA benchmarks for semantic segmentation we show that this is superior to a model without adaptation and to baseline approaches using statistics from the target domain only. Compared to standard UDA approaches we report a trade-off between performance and usage of source domain representations.