# Unsupervised Model Adaptation for Source-free Segmentation of Medical Images

arXiv: https://arxiv.org/abs/2211.00807 · HTML: https://mlsanity.com/paper/2211.00807/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 62 of its 99 references that are in the map.
- First posted on arXiv 2 Nov 2022.

## Builds on (most cited first, 30 of 62)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs](https://mlsanity.com/paper/1606.00915/) (2016)
- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [Adversarial Discriminative Domain Adaptation](https://mlsanity.com/paper/1702.05464/) (2017)
- [Deep Hashing Network for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1706.07522/) (2017)
- [CyCADA: Cycle-Consistent Adversarial Domain Adaptation](https://mlsanity.com/paper/1711.03213/) (2017)
- [Maximum Classifier Discrepancy for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1712.02560/) (2017)
- [Learning to Adapt Structured Output Space for Semantic Segmentation](https://mlsanity.com/paper/1802.10349/) (2018)
- [Fully-Convolutional Siamese Networks for Object Tracking](https://mlsanity.com/paper/1606.09549/) (2016)
- [Contrastive Adaptation Network for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1901.00976/) (2019)
- [Deep Learning for Medical Image Analysis](https://mlsanity.com/paper/1708.08987/) (2017)
- [Unsupervised Domain Adaptation with Residual Transfer Networks](https://mlsanity.com/paper/1602.04433/) (2016)
- [Unsupervised Pixel-Level Domain Adaptation with Generative Adversarial Networks](https://mlsanity.com/paper/1612.05424/) (2016)
- [Zero-Shot Semantic Segmentation](https://mlsanity.com/paper/1906.00817/) (2019)
- [Sliced Wasserstein Discrepancy for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1903.04064/) (2019)
- [Generalized Sliced Wasserstein Distances](https://mlsanity.com/paper/1902.00434/) (2019)
- [Neural Style Transfer: A Review](https://mlsanity.com/paper/1705.04058/) (2017)
- [Learning with a Wasserstein Loss](https://mlsanity.com/paper/1506.05439/) (2015)
- [Unsupervised Semantic Segmentation by Contrasting Object Mask Proposals](https://mlsanity.com/paper/2102.06191/) (2021)
- [Generate To Adapt: Aligning Domains using Generative Adversarial Networks](https://mlsanity.com/paper/1704.01705/) (2017)
- [Progressive Feature Alignment for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1811.08585/) (2018)
- [Source-Free Domain Adaptation for Semantic Segmentation](https://mlsanity.com/paper/2103.16372/) (2021)
- [Deep Reconstruction-Classification Networks for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1607.03516/) (2016)
- [Mind the Class Weight Bias: Weighted Maximum Mean Discrepancy for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1705.00609/) (2017)
- [Correlation Alignment for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1612.01939/) (2016)
- [Transferrable Prototypical Networks for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1904.11227/) (2019)

## Built on by (most cited first, 13 of 13)

- [Surgical Scene Understanding in the Era of Foundation AI Models: A Comprehensive Review](https://mlsanity.com/paper/2502.14886/) (2025)
- [Navigating Distribution Shifts in Medical Image Analysis: A Survey](https://mlsanity.com/paper/2411.05824/) (2024)
- [Harmonizing Flows: Leveraging normalizing flows for unsupervised and source-free MRI harmonization](https://mlsanity.com/paper/2407.15717/) (2024)
- [pMixFed: Efficient Personalized Federated Learning through Adaptive Layer-Wise Mixup](https://mlsanity.com/paper/2501.11002/) (2025)
- [Graph Harmony: Denoising and Nuclear-Norm Wasserstein Adaptation for Enhanced Domain Transfer in Graph-Structured Data](https://mlsanity.com/paper/2301.12361/) (2023)
- [FIESTA: Fourier-Based Semantic Augmentation with Uncertainty Guidance for Enhanced Domain Generalizability in Medical Image Segmentation](https://mlsanity.com/paper/2406.14308/) (2024)
- [Cross-Domain Distribution Alignment for Segmentation of Private Unannotated 3D Medical Images](https://mlsanity.com/paper/2410.09210/) (2024)
- [ProCal: Probability Calibration for Neighborhood-Guided Source-Free Domain Adaptation](https://mlsanity.com/paper/2603.18764/) (2026)
- [Robust Internal Representations for Domain Generalization](https://mlsanity.com/paper/2309.15522/) (2023)
- [Unsupervised Domain Adaptation Using Compact Internal Representations](https://mlsanity.com/paper/2401.07207/) (2024)
- [Curvature Diversity-Driven Deformation and Domain Alignment for Point Cloud](https://mlsanity.com/paper/2410.02720/) (2024)
- [Cross-domain Few-shot Object Detection with Multi-modal Textual Enrichment](https://mlsanity.com/paper/2502.16469/) (2025)
- [SymmAdapt: Symmetrical Flow Matching for Source-Free Domain Adaptation in Medical Image Segmentation](https://mlsanity.com/paper/2608.22532/) (2026)

## Abstract (arXiv)

The recent prevalence of deep neural networks has lead semantic segmentation networks to achieve human-level performance in the medical field when sufficient training data is provided. Such networks however fail to generalize when tasked with predicting semantic maps for out-of-distribution images, requiring model re-training on the new distributions. This expensive process necessitates expert knowledge in order to generate training labels. Distribution shifts can arise naturally in the medical field via the choice of imaging device, i.e. MRI or CT scanners. To combat the need for labeling images in a target domain after a model is successfully trained in a fully annotated textitsource domain with a different data distribution, unsupervised domain adaptation (UDA) can be used. Most UDA approaches ensure target generalization by creating a shared source/target latent feature space. This allows a source trained classifier to maintain performance on the target domain. However most UDA approaches require joint source and target data access, which may create privacy leaks with respect to patient information. We propose an UDA algorithm for medical image segmentation that does not require access to source data during adaptation, and is thus capable in maintaining patient data privacy. We rely on an approximation of the source latent features at adaptation time, and create a joint source/target embedding space by minimizing a distributional distance metric based on optimal transport. We demonstrate our approach is competitive to recent UDA medical segmentation works even with the added privacy requisite.