# UnDA: Unpaired Domain Alignment for Cross-Modal Knowledge Transfer in Medical Imaging

arXiv: https://arxiv.org/abs/2607.21546 · HTML: https://mlsanity.com/paper/2607.21546/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 23 references that are in the map.
- First posted on arXiv 23 Jul 2026.

## Builds on (most cited first, 13 of 13)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances](https://mlsanity.com/paper/1306.0895/) (2013)
- [Prototypical Contrastive Learning of Unsupervised Representations](https://mlsanity.com/paper/2005.04966/) (2020)
- [The RSNA-ASNR-MICCAI BraTS 2021 Benchmark on Brain Tumor Segmentation and Radiogenomic Classification](https://mlsanity.com/paper/2107.02314/) (2021)
- [DeepJDOT: Deep Joint Distribution Optimal Transport for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1803.10081/) (2018)
- [Unsupervised Bidirectional Cross-Modality Adaptation via Deeply Synergistic Image and Feature Alignment for Medical Image Segmentation](https://mlsanity.com/paper/2002.02255/) (2020)
- [Multivariate mixture model for myocardium segmentation combining multi-source images](https://mlsanity.com/paper/1612.08820/) (2016)
- [Synergistic Image and Feature Adaptation: Towards Cross-Modality Domain Adaptation for Medical Image Segmentation](https://mlsanity.com/paper/1901.08211/) (2019)
- [Unpaired Multi-modal Segmentation via Knowledge Distillation](https://mlsanity.com/paper/2001.03111/) (2020)
- [MAPSeg: Unified Unsupervised Domain Adaptation for Heterogeneous Medical Image Segmentation Based on 3D Masked Autoencoding and Pseudo-Labeling](https://mlsanity.com/paper/2303.09373/) (2023)
- [Colorectal Polyp Classification from White-light Colonoscopy Images via Domain Alignment](https://mlsanity.com/paper/2108.02476/) (2021)
- [Unpaired cross-modality educed distillation (CMEDL) for medical image segmentation](https://mlsanity.com/paper/2107.07985/) (2021)
- [CoMoTo: Unpaired Cross-Modal Lesion Distillation Improves Breast Lesion Detection in Tomosynthesis](https://mlsanity.com/paper/2407.17620/) (2024)

## Abstract (arXiv)

Multimodal based approaches often outperform single modality approaches in downstream tasks as the different modalities provide complementary information, yet acquiring paired clinical data remains a significant challenge in real world scenarios. While cross-modal knowledge distillation addresses this, existing methods often struggle with large modality gaps and the propagation of noise from uncertain source-domain predictions. To overcome these challenges, we propose UnDA, an anchor-guided framework for unpaired cross-modal distillation. Our approach introduces a backbone-agnostic Alignment Module that extracts semantically structured class tokens via an attention based pooling mechanism. To ensure robust knowledge transfer, we propose Uncertainty-Weighted Optimal Transport (UCT-OT), which dynamically weights feature-level alignment based on prediction confidence, effectively suppressing noisy supervision. Furthermore, a per-class ProtoNCE objective maintains stable prototype memories to enforce global discriminability across unpaired batches. Evaluations on representative segmentation tasks under strictly unpaired settings show consistent improvements in accuracy and boundary precision in the target modality, demonstrating that meaningful structural knowledge can be transferred across heterogeneous data sources without paired datasets.