arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2003.06054cs.CV
收藏

用于领域泛化的深度领域对抗图像生成

Deep Domain-Adversarial Image Generation for Domain Generalisation

University of Surrey(萨里大学);University of Edinburgh(爱丁堡大学);Samsung AI Center, Cambridge(三星人工智能中心(剑桥))

Kaiyang Zhou, Yongxin Yang, Timothy Hospedales, Tao Xiang

摘要:

机器学习模型在源数据集上进行训练并在不同分布的目标数据集上进行评估时,通常会遇到域偏移问题。为了克服这个问题,域泛化(DG)方法旨在利用来自多个源域的数据,以便经过训练的模型可以泛化到看不见的域。在本文中,我们提出了一种基于\emph{Deep Domain-Adversarial Image Generation}(DDAIG)的新型DG方法。具体而言,DDAIG由三个组件组成,即标签分类器,域分类器和域转换网络(DoTNet)。DoTNet的目标是将源训练数据映射到看不见的域。这是通过制定学习目标来实现的,以确保生成的数据可以被标签分类器正确分类,同时欺骗域分类器。通过用生成的不可见域数据扩充源训练数据,我们可以使标签分类器对未知域变化更鲁棒。在四个DG数据集上的实验证明了该方法的有效性。

英文摘要:

Machine learning models typically suffer from the domain shift problem when trained on a source dataset and evaluated on a target dataset of different distribution. To overcome this problem, domain generalisation (DG) methods aim to leverage data from multiple source domains so that a trained model can generalise to unseen domains. In this paper, we propose a novel DG approach based on \emph{Deep Domain-Adversarial Image Generation} (DDAIG). Specifically, DDAIG consists of three components, namely a label classifier, a domain classifier and a domain transformation network (DoTNet). The goal for DoTNet is to map the source training data to unseen domains. This is achieved by having a learning objective formulated to ensure that the generated data can be correctly classified by the label classifier while fooling the domain classifier. By augmenting the source training data with the generated unseen domain data, we can make the label classifier more robust to unknown domain changes. Extensive experiments on four DG datasets demonstrate the effectiveness of our approach.

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。

↑