Transforming the output of GANs by fine-tuning them with features from different datasets
This addresses a domain-specific problem for GAN users seeking to adapt models to new data distributions, but it appears incremental as it builds on existing fine-tuning methods.
The paper tackles the problem of transforming GAN outputs by fine-tuning pre-trained GANs with features from different datasets, resulting in a new distribution with novel characteristics, though no concrete numbers are provided.
In this work we present a method for fine-tuning pre-trained GANs with features from different datasets, resulting in the transformation of the output distribution into a new distribution with novel characteristics. The weights of the generator are updated using the weighted sum of the losses from a cross-dataset classifier and the frozen weights of the pre-trained discriminator. We discuss details of the technical implementation and share some of the visual results from this training process.