• Home
  • Search
  • A Curriculum-Style Self-Training Approach for Source-Free Semantic Segmentation.
  • Open Access IconOpen Access
  • Cite Icon15
  • https://doi.org/10.1109/tpami.2024.3432168Copy DOI Icon

A Curriculum-Style Self-Training Approach for Source-Free Semantic Segmentation.

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

Source-free domain adaptation has developed rapidly in recent years, where the well-trained source model is adapted to the target domain instead of the source data, offering the potential for privacy concerns and intellectual property protection. However, a number of feature alignment techniques in prior domain adaptation methods are not feasible in this challenging problem setting. Thereby, we resort to probing inherent domain-invariant feature learning and propose a curriculum-style self-training approach for source-free domain adaptive semantic segmentation. In particular, we introduce a curriculum-style entropy minimization method to explore the implicit knowledge from the source model, which fits the trained source model to the target data using certain information from easy-to-hard predictions. We then train the segmentation network by the proposed complementary curriculum-style self-training, which utilizes the negative and positive pseudo labels following the curriculum-learning manner. Although negative pseudo-labels with high uncertainty cannot be identified with the correct labels, they can definitely indicate absent classes. Moreover, we employ an information propagation scheme to further reduce the intra-domain discrepancy within the target domain, which could act as a standard post-processing method for the domain adaptation field. Furthermore, we extend the proposed method to a more challenging black-box source model scenario where only the source model's predictions are available. Extensive experiments validate that our method yields state-of-the-art performance on source-free semantic segmentation tasks for both synthetic-to-real and adverse conditions datasets.

Similar Papers
  • Conference Article
  • Citations1

Pseudo Features Guided Self-training for Domain Adaptive Semantic Segmentation of Aerial Images

  • May 17, 2023
  • Fahong Zhang +3
  • 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
  • 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
  • Conference Article
  • Citations95

Uncertainty-aware Pseudo Label Refinery for Domain Adaptive Semantic Segmentation

  • Oct 01, 2021
  • Yuxi Wang +2
  • Conference Article
  • Citations3

Different Approaches for Semantic Segmentation

  • Jun 01, 2020
  • Greeshma P.G
  • Research Article
  • Citations3

IPLC+: SAM-Guided Iterative Pseudo Label Correction for Source-Free Domain Adaptation in Medical Image Segmentation.

  • Dec 01, 2025
  • IEEE journal of biomedical and health informatics
  • Guoning Zhang +4
  • Conference Article
  • Citations260

Source-Free Domain Adaptation for Semantic Segmentation

  • Jun 01, 2021
  • Yuang Liu +2
  • Conference Article
  • Citations518

Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentation

  • Jun 01, 2021
  • Pan Zhang +5
  • Research Article
  • Citations29

I2F: A Unified Image-to-Feature Approach for Domain Adaptive Semantic Segmentation.

  • Mar 01, 2024
  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • Haoyu Ma +2
  • Research Article
  • Citations32

Uncertainty-Aware Source-Free Domain Adaptive Semantic Segmentation.

  • Jan 01, 2023
  • IEEE Transactions on Image Processing
  • Zhihe Lu +4
  • Research Article
  • Citations554

Rectifying Pseudo Label Learning via Uncertainty Estimation for Domain Adaptive Semantic Segmentation

  • Jan 06, 2021
  • International Journal of Computer Vision
  • Zhedong Zheng +1
  • Research Article
  • Citations19

Towards Source-Free Domain Adaptive Semantic Segmentation via Importance-Aware and Prototype-Contrast Learning

  • Apr 01, 2025
  • IEEE Transactions on Intelligent Vehicles
  • Yihong Cao +5
  • PDF
  • Research Article
  • Citations10

Utilization of deep learning tools to map and monitor biological soil crusts

  • Dec 12, 2023
  • Ecological Informatics
  • Stefan Herdy +3
  • Research Article
  • Citations2

Domain adaptation for semantic segmentation of road scenes via two-stage alignment of traffic elements

  • Oct 18, 2024
  • Neurocomputing
  • Yuan Gao +4
  • Research Article
  • Citations21

Source free unsupervised domain adaptation for electro-mechanical actuator fault diagnosis

  • Feb 24, 2023
  • Chinese Journal of Aeronautics
  • Jianyu Wang +2
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.