• Home
  • Search
  • W-ControlUDA: Weather-Controllable Diffusion-assisted Unsupervised Domain Adaptation for Semantic Segmentation
  • Cite Icon5
  • https://doi.org/10.1109/lra.2025.3544925Copy DOI Icon

W-ControlUDA: Weather-Controllable Diffusion-assisted Unsupervised Domain Adaptation for Semantic Segmentation

Show More
  • Abstract
  • Highlights & Summary
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Image generation has emerged as a potent strategy to enrich training data for unsupervised domain adaptation (UDA) of semantic segmentation in adverse weathers due to the scarcity of labelled target domain data. Previous UDA works commonly utilize generative adversarial networks (GANs) to translate images from the source to the target domain to enhance UDA training. However, these GANs, trained from scratch in an unpaired manner, produce sub-optimal image quality and lack multi-weather controllability. Consequently, controllable data generation for diverse weather scenarios remains underexplored. The recent strides in text-to-image diffusion models (DM) enables high fidelity diverse image generation conditioned on semantic labels. However, such DMs must be trained in a paired manner, i.e., image and label pairs, which poses huge challenge to the UDA setting where target domain labels are missing. This work addresses two key questions: <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">What is an optimal approach to train DMs for UDA, and how can the generated data best enhance UDA performance?</i> We introduce W-ControlUDA, a diffusion-assisted framework for UDA segmentation in adverse weather. W-ControlUDA involves two steps: DM training for data augmentation and UDA training using the generated data. Unlike previous unpaired training, our method conditions the DM on target predictions from a pre-trained segmentor, addressing the lack of target labels. We propose UDAControlNet for high-fidelity cross-domain and intra-domain data generation under adverse weathers. In UDA training, a label filtering mechanism is introduced to ensure more reliable results. W-ControlUDA helps UDA achieve a new milestone (72.8 mIoU) on the popular Cityscapes-to-ACDC benchmark and notably improves the model's generalization on 5 other benchmarks.

Similar Papers
  • Conference Article
  • Citations38

Source Data-free Unsupervised Domain Adaptation for Semantic Segmentation

  • Oct 17, 2021
  • Mucong Ye +3
  • Conference Article
  • Citations261

Self-Ensembling With GAN-Based Data Augmentation for Domain Adaptation in Semantic Segmentation

  • Oct 01, 2019
  • Jaehoon Choi +2
  • 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
  • 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
  • Citations15

Unsupervised Multitarget Domain Adaptation With Dictionary-Bridged Knowledge Exploitation.

  • Mar 01, 2024
  • IEEE Transactions on Neural Networks and Learning Systems
  • Qing Tian +5
  • PDF
  • Research Article
  • Citations240

Unsupervised Domain Adaptation Using Generative Adversarial Networks for Semantic Segmentation of Aerial Images

  • Jun 07, 2019
  • Remote Sensing
  • Bilel Benjdira +3
  • PDF
  • Research Article
  • Citations45

Data-Efficient Domain Adaptation for Semantic Segmentation of Aerial Imagery Using Generative Adversarial Networks

  • Feb 06, 2020
  • Applied Sciences
  • Bilel Benjdira +3
  • Research Article

PANDA: A Polarized Attention Network for Enhanced Unsupervised Domain Adaptation in Semantic Segmentation

  • Oct 31, 2024
  • Electronics
  • Chiao-Wen Kao +3
  • Book Chapter
  • Citations91

Domain Adaptive Semantic Segmentation Using Weak Labels

  • Jan 01, 2020
  • Sujoy Paul +4
  • Conference Article
  • Citations4

CompUDA: Compositional Unsupervised Domain Adaptation for Semantic Segmentation Under Adverse Conditions

  • Oct 01, 2023
  • Ziqiang Zhengl +3
  • Research Article
  • Citations42

Unsupervised Domain Adaptation for Semantic Segmentation by Content Transfer

  • May 18, 2021
  • Proceedings of the AAAI Conference on Artificial Intelligence
  • Suhyeon Lee +3
  • Research Article
  • Citations36

Generating Target Image-Label Pairs for Unsupervised Domain Adaptation

  • Jan 01, 2020
  • IEEE Transactions on Image Processing
  • Rui Li +3
  • Research Article
  • Citations2

Optimal transport-based domain adaptation for semantic segmentation of remote sensing images

  • Jan 16, 2024
  • International Journal of Remote Sensing
  • Ziyang Shen +3
  • Research Article
  • Citations12

EDRL: Entropy-guided disentangled representation learning for unsupervised domain adaptation in semantic segmentation

  • Jul 25, 2023
  • Computer Methods and Programs in Biomedicine
  • Runze Wang +2
  • Research Article
  • Citations31

Joint Adversarial Learning for Domain Adaptation in Semantic Segmentation

  • Apr 03, 2020
  • Proceedings of the AAAI Conference on Artificial Intelligence
  • Yixin Zhang +1
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.