StegoGAN: Leveraging Steganography for Non-Bijective Image-to-Image Translation
This addresses a challenge in computer vision for applications like domain adaptation, though it appears incremental as it builds on known steganography issues in CycleGAN methods.
The paper tackles the problem of non-bijective image-to-image translation, where conventional GANs hallucinate spurious features, by introducing StegoGAN, which leverages steganography to enhance semantic consistency and outperforms existing models in various tasks.
Most image-to-image translation models postulate that a unique correspondence exists between the semantic classes of the source and target domains. However, this assumption does not always hold in real-world scenarios due to divergent distributions, different class sets, and asymmetrical information representation. As conventional GANs attempt to generate images that match the distribution of the target domain, they may hallucinate spurious instances of classes absent from the source domain, thereby diminishing the usefulness and reliability of translated images. CycleGAN-based methods are also known to hide the mismatched information in the generated images to bypass cycle consistency objectives, a process known as steganography. In response to the challenge of non-bijective image translation, we introduce StegoGAN, a novel model that leverages steganography to prevent spurious features in generated images. Our approach enhances the semantic consistency of the translated images without requiring additional postprocessing or supervision. Our experimental evaluations demonstrate that StegoGAN outperforms existing GAN-based models across various non-bijective image-to-image translation tasks, both qualitatively and quantitatively. Our code and pretrained models are accessible at https://github.com/sian-wusidi/StegoGAN.