In this study, we delve into the task of few-shot Generative Domain Adaptation (GDA), which involves transferring a pre-trained generator from one domain to a new domain using only a few reference images. Inspired by the way human brains acquire knowledge in new domains, we present an innovative generator structure called Domain Re-Modulation (DoRM) .

However, the optimization aspect is not sufficient to achieve the success of stochastic minimax optimizationinmachinelearning.

Neural Information Processing Systems http://nips.cc/

While the main paper only contains proof sketches or intuitions, all complete proofsarereportedinAppendixA.

An illustration is provided inFigure 6. Asshowninalgorithm 1,there arethree main steps intheoverall procedure: first, we construct the coarse domain sequence by learning to predict the domain score for each example and sorting the examples according to the domain scores.

Concretely, we propose a coarse-to-fine framework, which starts with acoarsedomain discovery step via progressive domain discriminator training.