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

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.