• Home
  • Search
  • SF-City: A Source-Free Domain Adaptation Method for City-scale Point Cloud Semantic Segmentation
  • Cite Icon3
  • https://doi.org/10.1109/tmm.2025.3590934Copy DOI Icon

SF-City: A Source-Free Domain Adaptation Method for City-scale Point Cloud Semantic Segmentation

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

City-scale point cloud semantic segmentation is an important yet challenging task. Despite progress, existing methods rely heavily on point-wise annotations. An alternative solution is to apply the Unsupervised Domain Adaptation (UDA) approach. Recently, the 2D foundation model has achieved significant progress with training with internet-scale images. Therefore, adapting 2D foundation models to 3D City-scale point clouds is an attempting idea. Due to the data protection and storage issue, 2D source domain data is typically unavailable. Thus, we focus on Source-Free Domain Adaptation (SFDA) and propose a Source-Free City-scale point cloud semantic segmentation method, namely SF-City. Our method leverages knowledge from 2D pre-trained models to generate point-wise pseudo labels for training a 3D semantic segmentation network. We convert point clouds into remote-sensing-like images using Bird's-Eye-View (BEV) projection. However, directly using source models for pseudo label generation is hindered by domain gaps such as viewpoint variations, concept divergences, and geometry loss. To tackle these problems, we propose a Multi-scale Content Feature Extractor (MCFE) to extract holistic and contextual feature representations. Then, an Uncertainty-guided Inter-Model Feature Integrator (UIFI) is introduced to integrate inherent knowledge across source models. Furthermore, the Geometric-guided Pseudo Label Generator (GPLG) is leveraged to introduce geometric information to regulate pseudo labels. Through extensive experiments on two public benchmarks, SF-City demonstrates superior performance, achieving an mIoU of 28.8% on the SensatUrban dataset, outperforming recent state-of-the-art methods CLIPFO3D by about 6.3%.

Similar Papers
  • 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
  • Book Chapter
  • Citations1645

Unsupervised Domain Adaptation for Semantic Segmentation via Class-Balanced Self-training

  • Jan 01, 2018
  • Yang Zou +3
  • Book Chapter
  • Citations3

STRUDEL: Self-training with Uncertainty Dependent Label Refinement Across Domains

  • Jan 01, 2021
  • Fabian Gröger +2
  • 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
  • Citations43

Pseudo Labels for Unsupervised Domain Adaptation: A Review

  • Aug 03, 2023
  • Electronics
  • Yundong Li +2
  • Research Article
  • Citations3

A novel class restriction loss for unsupervised domain adaptation

  • Jul 20, 2021
  • Neurocomputing
  • Qi He +3
  • Conference Article
  • Citations166

Landmarks-based kernelized subspace alignment for unsupervised domain adaptation

  • May 18, 2015
  • Rahaf Aljundi +3
  • Research Article
  • Citations15

Unsupervised domain adaptation without source data for estimating occupancy and recognizing activities in smart buildings

  • Dec 01, 2023
  • Energy and Buildings
  • Jawher Dridi +2
  • Research Article
  • Citations5

Revisiting Domain-Adaptive Semantic Segmentation via Knowledge Distillation.

  • Jan 01, 2024
  • IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
  • Seongwon Jeong +3
  • Research Article
  • Citations3

Unsupervised global-local domain adaptation with self-training for remote sensing image semantic segmentation

  • Jan 20, 2025
  • International Journal of Remote Sensing
  • Junbo Zhang +3
  • Research Article

RAP2G: Relation-Aware Progressive Pseudo-label Generation for Cross-subject MI-EEG Recognition.

  • Jul 14, 2026
  • IEEE transactions on bio-medical engineering
  • Xinhui Li +6
  • Book Chapter
  • Citations66

Learning from Scale-Invariant Examples for Domain Adaptation in Semantic Segmentation

  • Jan 01, 2020
  • M Naseer Subhani +1
  • Research Article
  • Citations23

Pseudo Label Rectification via Co-Teaching and Decoupling for Multisource Domain Adaptation in Semantic Segmentation

  • Jan 01, 2022
  • IEEE Access
  • So Jeong Park +5
  • Dissertation

Label-efficient visual recognition with transfer learning

  • Jan 01, 2025
  • Jingyi Zhang
  • Conference Article
  • Citations85

MetaCorrection: Domain-aware Meta Loss Correction for Unsupervised Domain Adaptation in Semantic Segmentation

  • Jun 01, 2021
  • Xiaoqing Guo +3
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.