Model Adaptation: Unsupervised Domain Adaptation Without Source Data

2020-06-01

Computer Vision and Pattern Recognition

AI Summary

This paper addresses unsupervised model adaptation from a source domain to a target domain without access to any source-domain data or labels—termed *source-free* adaptation—aiming solely to improve the generalization of a pre-trained source model on unlabeled target data. To this end, we propose a Collaborative Class-Conditional Generative Adversarial Network (CC-GAN) framework: it models the semantic structure of the target domain via class-conditional generation; enforces weight constraints derived from the source model to preserve its discriminative capability; and incorporates clustering-driven feature regularization to enhance the discriminability of target-domain representations. Evaluated across multiple cross-domain vision tasks, our method achieves significant performance gains over conventional source-dependent adaptation approaches—using only unlabeled target data. It is the first to empirically validate the effectiveness, robustness, and scalability of model adaptation under the source-free setting.

Technology Category

• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Computer Vision: Generative Adversarial Networks (GANs) for Vision
• Natural Language Processing: Generation

Application Category

• User Modeling, Personalization and Recommendation: User modeling for targeted and personalized online advertising
• Web Mining and Content Analysis: Large pretrained models with web data
• Search and Retrieval-Augmented AI: Vertical and domain-specific search

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.

Problem

• Unsupervised domain adaptation without source data
• Improving target domain performance using unlabeled data
• Generating target-style data for model enhancement

Innovation

• Unsupervised domain adaptation
• Generative adversarial networks
• Clustering-based regularization