# Unpaired Image-to-Image Translation for Segmentation and Signal Unmixing

arXiv: https://arxiv.org/abs/2505.20746 · HTML: https://mlsanity.com/paper/2505.20746/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 62 references that are in the map.
- First posted on arXiv 27 May 2025.

## Builds on (most cited first, 29 of 29)

- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Progressive Growing of GANs for Improved Quality, Stability, and Variation](https://mlsanity.com/paper/1710.10196/) (2017)
- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [Spectral Normalization for Generative Adversarial Networks](https://mlsanity.com/paper/1802.05957/) (2018)
- [Group Normalization](https://mlsanity.com/paper/1803.08494/) (2018)
- [Learning Transferable Features with Deep Adaptation Networks](https://mlsanity.com/paper/1502.02791/) (2015)
- [Instance Normalization: The Missing Ingredient for Fast Stylization](https://mlsanity.com/paper/1607.08022/) (2016)
- [Least Squares Generative Adversarial Networks](https://mlsanity.com/paper/1611.04076/) (2016)
- [Multimodal Unsupervised Image-to-Image Translation](https://mlsanity.com/paper/1804.04732/) (2018)
- [Contrastive Learning for Unpaired Image-to-Image Translation](https://mlsanity.com/paper/2007.15651/) (2020)
- [Differentiable Augmentation for Data-Efficient GAN Training](https://mlsanity.com/paper/2006.10738/) (2020)
- [DRIT++: Diverse Image-to-Image Translation via Disentangled Representations](https://mlsanity.com/paper/1905.01270/) (2019)
- [Cell Detection with Star-convex Polygons](https://mlsanity.com/paper/1806.03535/) (2018)
- [Segment Anything Model for Medical Image Segmentation: Current Applications and Future Directions](https://mlsanity.com/paper/2401.03495/) (2024)
- [Stacked Generative Adversarial Networks](https://mlsanity.com/paper/1612.04357/) (2016)
- [Unsupervised Instance Segmentation in Microscopy Images via Panoptic Domain Adaptation and Task Re-weighting](https://mlsanity.com/paper/2005.02066/) (2020)
- [NuInsSeg: A Fully Annotated Dataset for Nuclei Instance Segmentation in H&E-Stained Histological Images](https://mlsanity.com/paper/2308.01760/) (2023)
- [Why Spectral Normalization Stabilizes GANs: Analysis and Improvements](https://mlsanity.com/paper/2009.02773/) (2020)
- [MicroSSIM: Improved Structural Similarity for Comparing Microscopy Data](https://mlsanity.com/paper/2408.08747/) (2024)
- [A comparative evaluation of image-to-image translation methods for stain transfer in histopathology](https://mlsanity.com/paper/2303.17009/) (2023)
- [Tight and Efficient Upper Bound on Spectral Norm of Convolutional Layers](https://mlsanity.com/paper/2409.11859/) (2024)
- [Mix-Domain Contrastive Learning for Unpaired H&E-to-IHC Stain Translation](https://mlsanity.com/paper/2406.11799/) (2024)
- [HistDiST: Histopathological Diffusion-based Stain Transfer](https://mlsanity.com/paper/2505.06793/) (2025)
- [Single-Step Bidirectional Unpaired Image Translation Using Implicit Bridge Consistency Distillation](https://mlsanity.com/paper/2503.15056/) (2025)
- [Image Translation Based Nuclei Segmentation for Immunohistochemistry Images](https://mlsanity.com/paper/2208.06202/) (2022)
- [DASGAN -- Joint Domain Adaptation and Segmentation for the Analysis of Epithelial Regions in Histopathology PD-L1 Images](https://mlsanity.com/paper/1906.11118/) (2019)
- [scSplit: Bringing Severity Cognizance to Image Decomposition in Fluorescence Microscopy](https://mlsanity.com/paper/2503.22983/) (2025)

## Built on by (most cited first, 1 of 1)

- [Unpaired Canonical Correlation Analysis](https://mlsanity.com/paper/2610.09530/) (2026)

## Abstract (arXiv)

This work introduces Ui2i, a novel model for unpaired image-to-image translation, trained on content-wise unpaired datasets to enable style transfer across domains while preserving content. Building on CycleGAN, Ui2i incorporates key modifications to better disentangle content and style features, and preserve content integrity. Specifically, Ui2i employs U-Net-based generators with skip connections to propagate localized shallow features deep into the generator. Ui2i removes feature-based normalization layers from all modules and replaces them with approximate bidirectional spectral normalization -- a parameter-based alternative that enhances training stability. To further support content preservation, channel and spatial attention mechanisms are integrated into the generators. Training is facilitated through image scale augmentation. Evaluation on two biomedical tasks -- domain adaptation for nuclear segmentation in immunohistochemistry (IHC) images and unmixing of biological structures superimposed in single-channel immunofluorescence (IF) images -- demonstrates Ui2i's ability to preserve content fidelity in settings that demand more accurate structural preservation than typical translation tasks. To the best of our knowledge, Ui2i is the first approach capable of separating superimposed signals in IF images using real, unpaired training data.