Transfer Learning with Pre-trained Conditional Generative Models

Transfer learning is crucial in training deep neural networks on new target tasks. Current transfer learning methods generally assume at least one of (i) source and target task label spaces must overlap, (ii) source datasets are available, and (iii) target network architectures are consistent with source ones. However, these all assumptions are difficult to hold in practical settings because the target task rarely has the same labels as the source task, the source dataset access is restricted due to licensing and storage costs, and the target architecture is often specialized to each task. To transfer source knowledge without these assumptions, we propose a transfer learning method that uses deep generative models and is composed of the following two stages: pseudo pre-training (PP) and pseudo semi-supervised learning (P-SSL). PP trains a target architecture with a synthesized dataset by using conditional source generative models. P-SSL applies SSL algorithms to labeled target data and unlabeled pseudo samples, which are generated by cascading the source classifier and generative models to condition them with target samples. Our experimental results indicate that our method can outperform baselines of scratch training and knowledge distillation.