arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2110.04545cs.LGcs.CV
收藏

面向无数据的领域泛化

Towards Data-Free Domain Generalization

Siemens Technology(西门子技术);University of Munich(慕尼黑大学);Technical University of Munich(慕尼黑工业大学)

Ahmed Frikha, Haokun Chen, Denis Krompaß, Thomas Runkler, Volker Tresp

摘要:

在这项工作中,我们研究了领域泛化(DG)和无数据学习的未探索的交叉点。特别是,我们解决的问题:如何将包含在不同的源域上训练的模型中的知识合并到一个单一的模型中,在没有源和目标域数据的情况下,该模型可以很好地推广到看不见的目标域?能够应对域转移的机器学习模型对于数据分布经常变化的真实场景至关重要。以前的DG方法通常依赖于使用源域数据,这使得它们不适合私有分散数据。我们定义了无数据领域泛化(DFDG)的新问题,这是一种实际的设置,在这种情况下,在源域上分别训练的模型可以代替原始数据集,并研究如何有效地解决这种情况下的领域泛化问题。我们提出DEKAN,一种方法,提取和融合特定领域的知识,从现有的教师模型到学生模型鲁棒域转移。我们的实证评估表明,我们的方法,实现了第一个国家的最先进的DFDG的结果显着优于无数据的知识蒸馏和合奏基线的有效性。

英文摘要:

In this work, we investigate the unexplored intersection of domain generalization (DG) and data-free learning. In particular, we address the question: How can knowledge contained in models trained on different source domains be merged into a single model that generalizes well to unseen target domains, in the absence of source and target domain data? Machine learning models that can cope with domain shift are essential for real-world scenarios with often changing data distributions. Prior DG methods typically rely on using source domain data, making them unsuitable for private decentralized data. We define the novel problem of Data-Free Domain Generalization (DFDG), a practical setting where models trained on the source domains separately are available instead of the original datasets, and investigate how to effectively solve the domain generalization problem in that case. We propose DEKAN, an approach that extracts and fuses domain-specific knowledge from the available teacher models into a student model robust to domain shift. Our empirical evaluation demonstrates the effectiveness of our method which achieves first state-of-the-art results in DFDG by significantly outperforming data-free knowledge distillation and ensemble baselines.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑