# Unsupervised Domain Adaptation via Similarity-based Prototypes for Cross-Modality Segmentation

arXiv: https://arxiv.org/abs/2510.20596 · HTML: https://mlsanity.com/paper/2510.20596/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 28 references that are in the map.
- First posted on arXiv 23 Oct 2025.

## Builds on (most cited first, 21 of 21)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [CyCADA: Cycle-Consistent Adversarial Domain Adaptation](https://mlsanity.com/paper/1711.03213/) (2017)
- [Least Squares Generative Adversarial Networks](https://mlsanity.com/paper/1611.04076/) (2016)
- [Learning to Adapt Structured Output Space for Semantic Segmentation](https://mlsanity.com/paper/1802.10349/) (2018)
- [Deep Learning for Medical Image Analysis](https://mlsanity.com/paper/1708.08987/) (2017)
- [Bidirectional Learning for Domain Adaptation of Semantic Segmentation](https://mlsanity.com/paper/1904.10620/) (2019)
- [Category Anchor-Guided Unsupervised Domain Adaptation for Semantic Segmentation](https://mlsanity.com/paper/1910.13049/) (2019)
- [Unsupervised Bidirectional Cross-Modality Adaptation via Deeply Synergistic Image and Feature Alignment for Medical Image Segmentation](https://mlsanity.com/paper/2002.02255/) (2020)
- [Synergistic Image and Feature Adaptation: Towards Cross-Modality Domain Adaptation for Medical Image Segmentation](https://mlsanity.com/paper/1901.08211/) (2019)
- [CrDoCo: Pixel-level Domain Transfer with Cross-Domain Consistency](https://mlsanity.com/paper/2001.03182/) (2020)
- [SynSeg-Net: Synthetic Segmentation Without Target Modality Ground Truth](https://mlsanity.com/paper/1810.06498/) (2018)
- [Self-Attentive Spatial Adaptive Normalization for Cross-Modality Domain Adaptation](https://mlsanity.com/paper/2103.03781/) (2021)
- [Margin Preserving Self-paced Contrastive Learning Towards Domain Adaptation for Medical Image Segmentation](https://mlsanity.com/paper/2103.08454/) (2021)
- [Contrastive Learning and Self-Training for Unsupervised Domain Adaptation in Semantic Segmentation](https://mlsanity.com/paper/2105.02001/) (2021)
- [Boundary-aware Supervoxel-level Iteratively Refined Interactive 3D Image Segmentation with Multi-agent Reinforcement Learning](https://mlsanity.com/paper/2303.10692/) (2023)
- [Maximizing Cosine Similarity Between Spatial Features for Unsupervised Domain Adaptation in Semantic Segmentation](https://mlsanity.com/paper/2102.13002/) (2021)
- [Adapt Everywhere: Unsupervised Adaptation of Point-Clouds and Entropy Minimisation for Multi-modal Cardiac Image Segmentation](https://mlsanity.com/paper/2103.08219/) (2021)
- [Transforming the Interactive Segmentation for Medical Imaging](https://mlsanity.com/paper/2208.09592/) (2022)
- [Multi-sequence Cardiac MR Segmentation with Adversarial Domain Adaptation Network](https://mlsanity.com/paper/1910.12514/) (2019)

## Abstract (arXiv)

Deep learning models have achieved great success on various vision challenges, but a well-trained model would face drastic performance degradation when applied to unseen data. Since the model is sensitive to domain shift, unsupervised domain adaptation attempts to reduce the domain gap and avoid costly annotation of unseen domains. This paper proposes a novel framework for cross-modality segmentation via similarity-based prototypes. In specific, we learn class-wise prototypes within an embedding space, then introduce a similarity constraint to make these prototypes representative for each semantic class while separable from different classes. Moreover, we use dictionaries to store prototypes extracted from different images, which prevents the class-missing problem and enables the contrastive learning of prototypes, and further improves performance. Extensive experiments show that our method achieves better results than other state-of-the-art methods.