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

arXiv: https://arxiv.org/abs/2109.14219 · HTML: https://mlsanity.com/paper/2109.14219/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 10 references that are in the map.
- First posted on arXiv 29 Sep 2021.

## Builds on (most cited first, 6 of 6)

- [CyCADA: Cycle-Consistent Adversarial Domain Adaptation](https://mlsanity.com/paper/1711.03213/) (2017)
- [Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks](https://mlsanity.com/paper/1703.10593/) (2017)
- [Bidirectional Learning for Domain Adaptation of Semantic Segmentation](https://mlsanity.com/paper/1904.10620/) (2019)
- [Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2101.10979/) (2021)
- [Reusing Discriminators for Encoding: Towards Unsupervised Image-to-Image Translation](https://mlsanity.com/paper/2003.00273/) (2020)
- [Pixel-Level Cycle Association: A New Perspective for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2011.00147/) (2020)

## Built on by (most cited first, 16 of 16)

- [CrossMoDA 2021 challenge: Benchmark of Cross-Modality Domain Adaptation techniques for Vestibular Schwannoma and Cochlea Segmentation](https://mlsanity.com/paper/2201.02831/) (2022)
- [COSMOS: Cross-Modality Unsupervised Domain Adaptation for 3D Medical Image Segmentation based on Target-aware Domain Translation and Iterative Self-Training](https://mlsanity.com/paper/2203.16557/) (2022)
- [COSST: Multi-organ Segmentation with Partially Labeled Datasets Using Comprehensive Supervisions and Self-training](https://mlsanity.com/paper/2304.14030/) (2023)
- [Unsupervised Cross-Modality Domain Adaptation for Vestibular Schwannoma Segmentation and Koos Grade Prediction based on Semi-Supervised Contrastive Learning](https://mlsanity.com/paper/2210.04255/) (2022)
- [Multi-view Cross-Modality MR Image Translation for Vestibular Schwannoma and Cochlea Segmentation](https://mlsanity.com/paper/2303.14998/) (2023)
- [Enhancing Data Diversity for Self-training Based Unsupervised Cross-modality Vestibular Schwannoma and Cochlea Segmentation](https://mlsanity.com/paper/2209.11879/) (2022)
- [Learning Site-specific Styles for Multi-institutional Unsupervised Cross-modality Domain Adaptation](https://mlsanity.com/paper/2311.12437/) (2023)
- [An Unpaired Cross-modality Segmentation Framework Using Data Augmentation and Hybrid Convolutional Networks for Segmenting Vestibular Schwannoma and Cochlea](https://mlsanity.com/paper/2211.14986/) (2022)
- [Weakly Unsupervised Domain Adaptation for Vestibular Schwannoma Segmentation](https://mlsanity.com/paper/2303.07093/) (2023)
- [Dual-level Interaction for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2307.07972/) (2023)
- [Fine-Grained Unsupervised Cross-Modality Domain Adaptation for Vestibular Schwannoma Segmentation](https://mlsanity.com/paper/2311.15090/) (2023)
- [Image Translation-Based Unsupervised Cross-Modality Domain Adaptation for Medical Image Segmentation](https://mlsanity.com/paper/2502.15193/) (2025)
- [crossMoDA Challenge: Evolution of Cross-Modality Domain Adaptation Techniques for Vestibular Schwannoma and Cochlea Segmentation from 2021 to 2023](https://mlsanity.com/paper/2506.12006/) (2025)
- [Koos Classification of Vestibular Schwannoma via Image Translation-Based Unsupervised Cross-Modality Domain Adaptation](https://mlsanity.com/paper/2303.07674/) (2023)
- [Image-level supervision and self-training for transformer-based cross-modality tumor segmentation](https://mlsanity.com/paper/2309.09246/) (2023)
- [IntraStyler: Intra-Domain Style Synthesis for Cross-Modality MRI Domain Adaptation](https://mlsanity.com/paper/2601.00212/) (2026)

## Abstract (arXiv)

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.