• Home
  • Search
  • Consistency Regularization with High-dimensional Non-adversarial Source-guided Perturbation for Unsupervised Domain Adaptation in Segmentation
  • Cite Icon15
  • https://doi.org/10.1609/aaai.v35i11.17216Copy DOI Icon

Consistency Regularization with High-dimensional Non-adversarial Source-guided Perturbation for Unsupervised Domain Adaptation in Segmentation

Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Unsupervised domain adaptation for semantic segmentation has been intensively studied due to the low cost of the pixel-level annotation for synthetic data. The most common approaches try to generate images or features mimicking the distribution in the target domain while preserving the semantic contents in the source domain so that a model can be trained with annotations from the latter. However, such methods highly rely on an image translator or feature extractor trained in an elaborated mechanism including adversarial training, which brings in extra complexity and instability in the adaptation process. Furthermore, these methods mainly focus on taking advantage of the labeled source dataset, leaving the unlabeled target dataset not fully utilized. In this paper, we propose a bidirectional style-induced domain adaptation method, called BiSIDA, that employs consistency regularization to efficiently exploit information from the unlabeled target domain dataset, requiring only a simple neural style transfer model. BiSIDA aligns domains by not only transferring source images into the style of target images but also transferring target images into the style of source images to perform high-dimensional perturbation on the unlabeled target images, which is crucial to the success in applying consistency regularization in segmentation tasks. Extensive experiments show that our BiSIDA achieves new state-of-the-art on two commonly-used synthetic-to-real domain adaptation benchmarks: GTA5-to-CityScapes and SYNTHIA-to-CityScapes. Code and pretrained style transfer model are available at: https://github.com/wangkaihong/BiSIDA.

Similar Papers
  • Conference Article
  • Citations38

Source Data-free Unsupervised Domain Adaptation for Semantic Segmentation

  • Oct 17, 2021
  • Mucong Ye +3
  • 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
  • Citations22

Continual Unsupervised Domain Adaptation for Semantic Segmentation by Online Frequency Domain Style Transfer

  • Sep 19, 2021
  • Jan-Aike Termohlen +4
  • Research Article
  • Citations37

Unsupervised Adversarial Domain Adaptation Network for Semantic Segmentation

  • Dec 26, 2019
  • IEEE Geoscience and Remote Sensing Letters
  • Wei Liu +1
  • Conference Article
  • Citations1

Domain Adaptive Semantic Segmentation via Image Translation and Representation Alignment

  • Sep 01, 2021
  • Jingxuan Kang +2
  • 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
  • Citations47

DecoupleNet: Decoupled Network for Domain Adaptive Semantic Segmentation

  • Jan 01, 2022
  • Xin Lai +7
  • Conference Article
  • Citations4

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

  • Oct 01, 2023
  • Ziqiang Zhengl +3
  • Dissertation

Label-efficient visual recognition with transfer learning

  • Jan 01, 2025
  • Jingyi Zhang
  • 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
  • Book Chapter
  • Citations97

Label-Driven Reconstruction for Domain Adaptation in Semantic Segmentation

  • Jan 01, 2020
  • Jinyu Yang +5
  • Book Chapter
  • Citations8

Domain Adaptation for Eye Segmentation

  • Jan 01, 2020
  • Yiru Shen +2
  • PDF
  • Research Article
  • Citations4

Class-conditional domain adaptation for semantic segmentation

  • Mar 22, 2024
  • Computational Visual Media
  • Yue Wang +4
  • Research Article
  • Citations14

Semantic Consistent Embedding for Domain Adaptive Zero-Shot Learning.

  • Jan 01, 2023
  • IEEE Transactions on Image Processing
  • Jianyang Zhang +4
  • Conference Article
  • Citations56

Multi-Anchor Active Domain Adaptation for Semantic Segmentation

  • Oct 01, 2021
  • Munan Ning +7
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.