仅用目标域无标签数据，提升预训练模型在新场景的性能。
Model Adaptation: Unsupervised Domain Adaptation without Source Data
- 通过生成目标风格数据，让模型与生成器协同优化，无需源数据。
- 在多个任务上超越传统方法，实现无源数据下的高效迁移。
- 适合隐私敏感场景，如医疗、金融等无法获取源数据的领域。
本文研究一种挑战性设置——无监督模型自适应：仅依赖无标签目标数据，提升已有源模型在目标域的表现，以应对因数据隐私问题导致源数据不可用的现实场景。为此，提出一种新框架——协作类别条件生成对抗网络（collaborative class conditional generative adversarial net），通过生成目标风格数据来指导模型优化，使生成器与预测模型在无源数据条件下实现协同改进。针对缺乏源数据监督的问题，引入权重约束以保持与源模型相似性，并采用基于聚类的正则化增强目标域特征判别力。实验表明，在多个适配任务中，该方法仅使用无标签目标数据即取得优于传统域自适应方法的效果，验证了其在该挑战性设置下的有效性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。