I2I-Galip: Unsupervised Medical Image Translation Using Generative Adversarial CLIP

Yilmaz Korkmaz, Vishal M. Patel

Keywords: image translation, unsupervised learning, generative adversarial models

TL;DR: A CLIP guided image translation framework for unsupervised medical image translation

Abstract: Unpaired image-to-image translation is a challenging task due to the absence of paired examples, which complicates learning the complex mappings between the distinct distributions of the source and target domains. One of the most commonly used approaches for this task is cycle-consistent models which require the training of a new pair of generator-discriminator networks for each translation. In this paper, we propose a new image-to-image translation framework named Image-to-Image-Generative-Adversarial-CLIP (I2I-Galip) where we utilize pre-trained multi-modal foundation models to mitigate the need of separate generator-discriminator pairs for each source-target mapping while achieving better and more efficient multi-domain translation. By utilizing the massive knowledge gathered during pre-training a foundation model, our approach makes use of a single lightweight generator network with $\approx$13M parameters for the multi-domain image translation task. Comprehensive experiments on translation performance in public MRI and CT datasets show the superior performance of the proposed framework over the existing approaches.

Primary Subject Area: Image Synthesis

Secondary Subject Area: Unsupervised Learning and Representation Learning

Paper Type: Methodological Development

Registration Requirement: Yes

Reproducibility: https://github.com/yilmazkorkmaz1/I2I-Galip

Visa & Travel: Yes

Midl Latex Submission Checklist: Ensure no LaTeX errors during compilation., Created a single midl25_NNN.zip file with midl25_NNN.tex, midl25_NNN.bib, all necessary figures and files., Includes \documentclass{midl}, \jmlryear{2025}, \jmlrworkshop, \jmlrvolume, \editors, and correct \bibliography command., Did not override options of the hyperref package, Did not use the times package., All authors and co-authors are correctly listed with proper spelling and avoid Unicode characters., Author and institution details are de-anonymized where needed. All author names, affiliations, and paper title are correctly spelled and capitalized in the biography section., References must use the .bib file. Did not override the bibliographystyle defined in midl.cls. Did not use \begin{thebibliography} directly to insert references., Tables and figures do not overflow margins; avoid using \scalebox; used \resizebox when needed., Included all necessary figures and removed *unused* files in the zip archive., Removed special formatting, visual annotations, and highlights used during rebuttal., All special characters in the paper and .bib file use LaTeX commands (e.g., \'e for é)., Appendices and supplementary material are included in the same PDF after references., Main paper does not exceed 9 pages; acknowledgements, references, and appendix start on page 10 or later.

Submission Number: 45