Unsupervised Domain Adaptation in Semantic Segmentation Based on Pixel Alignment and Self-Training

2021/09/29 by Hexin Dong, Dong, Hexin, F. Richard Yu +7 · 1 citation
Computer Science · #Advanced Neural Network Applications #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Generative Adversarial Networks and Image Synthesis

paper · pdf · doi:10.48550/arxiv.2109.14219

openalex publication_date 2021/09/29 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

This paper proposes an unsupervised cross-modality domain adaptation approach based on pixel alignment and self-training. Pixel alignment transfers ceT1 scans to hrT2 modality, helping to reduce domain shift in the training segmentation model. Self-training adapts the decision boundary of the segmentation network to fit the distribution of hrT2 scans. Experiment results show that PAST has outperformed the non-UDA baseline significantly, and it received rank-2 on CrossMoDA validation phase Leaderboard with a mean Dice score of 0.8395.

Citations

• Pixel-Level Cycle Association: A New Perspective for Domain Adaptive Semantic Segmentation

Cited by

• crossMoDA Challenge: Evolution of Cross-Modality Domain Adaptation Techniques for Vestibular Schwannoma and Cochlea Segmentation from 2021 to 2023

Related

• Cross-Region Domain Adaptation for Class-level Alignment
• Unsupervised Domain Adaptation through Self-Supervision
• Exploiting Inter-pixel Correlations in Unsupervised Domain Adaptation for Semantic Segmentation
• PiPa: Pixel- and Patch-wise Self-supervised Learning for Domain Adaptative Semantic Segmentation
• PiPa++: Towards Unification of Domain Adaptive Semantic Segmentation via Self-supervised Learning