# AV-GAN: Attention-Based Varifocal Generative Adversarial Network for Uneven Medical Image Translation

arXiv: https://arxiv.org/abs/2404.10714 · HTML: https://mlsanity.com/paper/2404.10714/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 32 references that are in the map.
- First posted on arXiv 16 Apr 2024.

## Builds on (most cited first, 20 of 20)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Demystifying MMD GANs](https://mlsanity.com/paper/1801.01401/) (2018)
- [StarGAN v2: Diverse Image Synthesis for Multiple Domains](https://mlsanity.com/paper/1912.01865/) (2019)
- [Self-Attention Generative Adversarial Networks](https://mlsanity.com/paper/1805.08318/) (2018)
- [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)
- [Few-Shot Unsupervised Image-to-Image Translation](https://mlsanity.com/paper/1905.01723/) (2019)
- [GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium](https://mlsanity.com/paper/1706.08500/) (2017)
- [U-GAT-IT: Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translation](https://mlsanity.com/paper/1907.10830/) (2019)
- [Deep learning-based virtual histology staining using auto-fluorescence of label-free tissue](https://mlsanity.com/paper/1803.11293/) (2018)
- [Deep learning-based transformation of the H&E stain into special stains](https://mlsanity.com/paper/2008.08871/) (2020)
- [QS-Attn: Query-Selected Attention for Contrastive Learning in I2I Translation](https://mlsanity.com/paper/2203.08483/) (2022)
- [Diagonal Attention and Style-based GAN for Content-Style Disentanglement in Image Generation and Translation](https://mlsanity.com/paper/2103.16146/) (2021)
- [Multi-marginal Wasserstein GAN](https://mlsanity.com/paper/1911.00888/) (2019)
- [Adversarial Alignment for Source Free Object Detection](https://mlsanity.com/paper/2301.04265/) (2023)
- [Fre-GAN: Adversarial Frequency-consistent Audio Synthesis](https://mlsanity.com/paper/2106.02297/) (2021)
- [Improving GANs with A Dynamic Discriminator](https://mlsanity.com/paper/2209.09897/) (2022)
- [Virtual stain transfer in histology via cascaded deep neural networks](https://mlsanity.com/paper/2207.06578/) (2022)
- [Deep Learning-based Frozen Section to FFPE Translation](https://mlsanity.com/paper/2107.11786/) (2021)

## Built on by (most cited first, 3 of 3)

- [Unpaired Multi-Domain Histopathology Virtual Staining using Dual Path Prompted Inversion](https://mlsanity.com/paper/2412.11106/) (2024)
- [Content Generation Models in Computational Pathology: A Comprehensive Survey on Methods, Applications, and Challenges](https://mlsanity.com/paper/2505.10993/) (2025)
- [From Pixels to Pathology: Restoration Diffusion for Diagnostic-Consistent Virtual IHC](https://mlsanity.com/paper/2508.02528/) (2025)

## Abstract (arXiv)

Different types of staining highlight different structures in organs, thereby assisting in diagnosis. However, due to the impossibility of repeated staining, we cannot obtain different types of stained slides of the same tissue area. Translating the slide that is easy to obtain (e.g., H&E) to slides of staining types difficult to obtain (e.g., MT, PAS) is a promising way to solve this problem. However, some regions are closely connected to other regions, and to maintain this connection, they often have complex structures and are difficult to translate, which may lead to wrong translations. In this paper, we propose the Attention-Based Varifocal Generative Adversarial Network (AV-GAN), which solves multiple problems in pathologic image translation tasks, such as uneven translation difficulty in different regions, mutual interference of multiple resolution information, and nuclear deformation. Specifically, we develop an Attention-Based Key Region Selection Module, which can attend to regions with higher translation difficulty. We then develop a Varifocal Module to translate these regions at multiple resolutions. Experimental results show that our proposed AV-GAN outperforms existing image translation methods with two virtual kidney tissue staining tasks and improves FID values by 15.9 and 4.16 respectively in the H&E-MT and H&E-PAS tasks.