# Ultra-high-resolution unpaired stain transformation via Kernelized Instance Normalization

arXiv: https://arxiv.org/abs/2208.10730 · HTML: https://mlsanity.com/paper/2208.10730/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 32 references that are in the map.
- First posted on arXiv 23 Aug 2022.

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

- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Instance Normalization: The Missing Ingredient for Fast Stylization](https://mlsanity.com/paper/1607.08022/) (2016)
- [Contrastive Learning for Unpaired Image-to-Image Translation](https://mlsanity.com/paper/2007.15651/) (2020)
- [A Learned Representation For Artistic Style](https://mlsanity.com/paper/1610.07629/) (2016)
- [DualGAN: Unsupervised Dual Learning for Image-to-Image Translation](https://mlsanity.com/paper/1704.02510/) (2017)
- [Learning to Discover Cross-Domain Relations with Generative Adversarial Networks](https://mlsanity.com/paper/1703.05192/) (2017)
- [Image-to-Image Translation: Methods and Applications](https://mlsanity.com/paper/2101.08629/) (2021)
- [One-Sided Unsupervised Domain Mapping](https://mlsanity.com/paper/1706.00826/) (2017)
- [The Spatially-Correlative Loss for Various Image Translation Tasks](https://mlsanity.com/paper/2104.00854/) (2021)
- [Deep learning-based transformation of the H&E stain into special stains](https://mlsanity.com/paper/2008.08871/) (2020)
- [Towards Ultra-Resolution Neural Style Transfer via Thumbnail Instance Normalization](https://mlsanity.com/paper/2103.11784/) (2021)
- [Virtualization of tissue staining in digital pathology using an unsupervised deep learning approach](https://mlsanity.com/paper/1810.06415/) (2018)
- [DASGAN -- Joint Domain Adaptation and Segmentation for the Analysis of Epithelial Regions in Histopathology PD-L1 Images](https://mlsanity.com/paper/1906.11118/) (2019)

## Built on by (most cited first, 5 of 5)

- [Every Pixel Has its Moments: Ultra-High-Resolution Unpaired Image-to-Image Translation via Dense Normalization](https://mlsanity.com/paper/2407.04245/) (2024)
- [Digital Staining with Knowledge Distillation: A Unified Framework for Unpaired and Paired-But-Misaligned Data](https://mlsanity.com/paper/2504.09899/) (2025)
- [Image Translation with Kernel Prediction Networks for Semantic Segmentation](https://mlsanity.com/paper/2507.08554/) (2025)
- [Two-Stage Cross-Domain Cervical Abnormality Screening with Cytopathological Image Synthesis and Knowledge Distillation](https://mlsanity.com/paper/2606.27678/) (2026)
- [Seamless Whole Slide Label-Free Virtual Staining](https://mlsanity.com/paper/2609.10914/) (2026)

## Abstract (arXiv)

While hematoxylin and eosin (H&E) is a standard staining procedure, immunohistochemistry (IHC) staining further serves as a diagnostic and prognostic method. However, acquiring special staining results requires substantial costs. Hence, we proposed a strategy for ultra-high-resolution unpaired image-to-image translation: Kernelized Instance Normalization (KIN), which preserves local information and successfully achieves seamless stain transformation with constant GPU memory usage. Given a patch, corresponding position, and a kernel, KIN computes local statistics using convolution operation. In addition, KIN can be easily plugged into most currently developed frameworks without re-training. We demonstrate that KIN achieves state-of-the-art stain transformation by replacing instance normalization (IN) layers with KIN layers in three popular frameworks and testing on two histopathological datasets. Furthermore, we manifest the generalizability of KIN with high-resolution natural images. Finally, human evaluation and several objective metrics are used to compare the performance of different approaches. Overall, this is the first successful study for the ultra-high-resolution unpaired image-to-image translation with constant space complexity. Code is available at: https://github.com/Kaminyou/URUST