Model Adaptation: Unsupervised Domain Adaptation Without Source Data

TLDR

The study addresses unsupervised domain adaptation where only unlabeled target data is available, a scenario motivated by data privacy concerns that preclude access to labeled source data. The authors aim to develop an unsupervised model adaptation method that improves a source prediction model on the target domain using only unlabeled target data. They propose a collaborative class‑conditional GAN that generates target‑style data to refine the prediction model, supplemented by a weight constraint to preserve source similarity and clustering‑based regularization for discriminative target features. The method enables source‑model and generator collaboration without source data and outperforms conventional domain adaptation techniques on several tasks using only unlabeled target data.

Abstract

In this paper, we investigate a challenging unsupervised domain adaptation setting --- unsupervised model adaptation. We aim to explore how to rely only on unlabeled target data to improve performance of an existing source prediction model on the target domain, since labeled source data may not be available in some real-world scenarios due to data privacy issues. For this purpose, we propose a new framework, which is referred to as collaborative class conditional generative adversarial net to bypass the dependence on the source data. Specifically, the prediction model is to be improved through generated target-style data, which provides more accurate guidance for the generator. As a result, the generator and the prediction model can collaborate with each other without source data. Furthermore, due to the lack of supervision from source data, we propose a weight constraint that encourages similarity to the source model. A clustering-based regularization is also introduced to produce more discriminative features in the target domain. Compared to conventional domain adaptation methods, our model achieves superior performance on multiple adaptation tasks with only unlabeled target data, which verifies its effectiveness in this challenging setting.