# Aligning What You Separate: Denoised Patch Mixing for Source-Free Domain Adaptation in Medical Image Segmentation

arXiv: https://arxiv.org/abs/2510.25227 · HTML: https://mlsanity.com/paper/2510.25227/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 13 references that are in the map.
- First posted on arXiv 29 Oct 2025.

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

- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [REFUGE Challenge: A Unified Framework for Evaluating Automated Methods for Glaucoma Assessment from Fundus Photographs](https://mlsanity.com/paper/1910.03667/) (2019)
- [A Comprehensive Survey on Source-free Domain Adaptation](https://mlsanity.com/paper/2302.11803/) (2023)
- [Source-Free Domain Adaptive Fundus Image Segmentation with Denoised Pseudo-Labeling](https://mlsanity.com/paper/2109.09735/) (2021)
- [Boundary and Entropy-driven Adversarial Learning for Fundus Image Segmentation](https://mlsanity.com/paper/1906.11143/) (2019)
- [Context-Aware Pseudo-Label Refinement for Source-Free Domain Adaptive Fundus Image Segmentation](https://mlsanity.com/paper/2308.07731/) (2023)

## Abstract (arXiv)

Source-Free Domain Adaptation (SFDA) is emerging as a compelling solution for medical image segmentation under privacy constraints, yet current approaches often ignore sample difficulty and struggle with noisy supervision under domain shift. We present a new SFDA framework that leverages Hard Sample Selection and Denoised Patch Mixing to progressively align target distributions. First, unlabeled images are partitioned into reliable and unreliable subsets through entropy-similarity analysis, allowing adaptation to start from easy samples and gradually incorporate harder ones. Next, pseudo-labels are refined via Monte Carlo-based denoising masks, which suppress unreliable pixels and stabilize training. Finally, intra- and inter-domain objectives mix patches between subsets, transferring reliable semantics while mitigating noise. Experiments on benchmark datasets show consistent gains over prior SFDA and UDA methods, delivering more accurate boundary delineation and achieving state-of-the-art Dice and ASSD scores. Our study highlights the importance of progressive adaptation and denoised supervision for robust segmentation under domain shift.