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.

The effectiveness of unsupervised domain adaptation degrades when there is a large discrepancy between the source and target domains. Gradual domain adaption (GDA) is one promising way to mitigate such an issue, by leveraging additional unlabeled data that gradually shift from the source to the target. Through sequentially adapting the model along the indexed intermediate domains, GDA substantially improves the overall adaptation performance. In practice, however, the extra unlabeled data may not be separated into intermediate domains and indexed properly, limiting the applicability of GDA. In this paper, we investigate how to discover the sequence of intermediate domains when it is not already available.