• Home
  • Search
  • Unsupervised BatchNorm Adaptation (UBNA): A Domain Adaptation Method for Semantic Segmentation Without Using Source Domain Representations
  • Open Access IconOpen Access
  • Cite Icon37
  • https://doi.org/10.1109/wacvw54805.2022.00027Copy DOI Icon

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

  • Jan 1, 2022
  • Marvin Klingner +3 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

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. <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sup> <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sup> Code is available at https://git;hub.com/ifnspaml/UBNR

Similar Papers
  • Research Article
  • Citations37

Unsupervised Adversarial Domain Adaptation Network for Semantic Segmentation

  • Dec 26, 2019
  • IEEE Geoscience and Remote Sensing Letters
  • Wei Liu +1
  • Research Article
  • Citations30

Unsupervised adversarial domain adaptation with similarity diffusion for person re-identification

  • Dec 16, 2020
  • Neurocomputing
  • Geyu Tang +3
  • Research Article
  • Citations6

Cross-Domain Urban Land Use Classification via Scenewise Unsupervised Multisource Domain Adaptation With Transformer

  • Jan 01, 2024
  • IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
  • Mengmeng Li +3
  • Research Article
  • Citations15

Feature Re-Representation and Reliable Pseudo Label Retraining for Cross-Domain Semantic Segmentation.

  • Mar 01, 2024
  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • Jing Li +5
  • Research Article
  • Citations7

Unsupervised Domain Expansion for Visual Categorization

  • Nov 12, 2021
  • ACM Transactions on Multimedia Computing, Communications, and Applications
  • Jie Wang +4
  • Conference Article
  • Citations38

Source Data-free Unsupervised Domain Adaptation for Semantic Segmentation

  • Oct 17, 2021
  • Mucong Ye +3
  • PDF
  • Research Article
  • Citations47

Unsupervised Domain Adaptation by Statistics Alignment for Deep Sleep Staging Networks.

  • Jan 01, 2022
  • IEEE Transactions on Neural Systems and Rehabilitation Engineering
  • Jiahao Fan +8
  • Dissertation

Label-efficient visual recognition with transfer learning

  • Jan 01, 2025
  • Jingyi Zhang
  • Research Article

Adaptive integrated weight unsupervised multi-source domain adaptation without source data

  • Apr 22, 2025
  • Complex & Intelligent Systems
  • Zhirui Wang +2
  • Research Article
  • Citations47

Adapt Everywhere: Unsupervised Adaptation of Point-Clouds and Entropy Minimization for Multi-Modal Cardiac Image Segmentation.

  • Jul 01, 2021
  • IEEE transactions on medical imaging
  • Sulaiman Vesal +4
  • PDF
  • Supplementary Content
  • Citations68

Deep Unsupervised Domain Adaptation with Time Series Sensor Data: A Survey

  • Jul 23, 2022
  • Sensors (Basel, Switzerland)
  • Yongjie Shi +2
  • Research Article

Tight Source Domain Match for Partial Domain Adaptation Based on Maximum Density

  • May 01, 2022
  • Journal of Physics Conference Series
  • Zi-Ao Ni +4
  • Research Article
  • Citations17

DASRSNet: Multitask Domain Adaptation for Super-Resolution-Aided Semantic Segmentation of Remote Sensing Images

  • Jan 01, 2023
  • IEEE Transactions on Geoscience and Remote Sensing
  • Yuxiang Cai +4
  • Conference Article
  • Citations24

Joint Progressive Knowledge Distillation and Unsupervised Domain Adaptation

  • Jul 01, 2020
  • Espace ÉTS (ETS)
  • Le Thanh Nguyen-Meidine +4
  • PDF
  • Research Article
  • Citations13

Continual BatchNorm Adaptation (CBNA) for Semantic Segmentation

  • Nov 01, 2022
  • IEEE Transactions on Intelligent Transportation Systems
  • Marvin Klingner +2
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.