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 1902.00113cs.CV
收藏

领域泛化的情景训练

Episodic Training for Domain Generalization

Samsung AI Center(三星人工智能中心);University of Surrey(萨里大学);University of Science and Technology of China(中国科学技术大学);iFlytek Research(科大讯飞研究院);University of Edinburgh(爱丁堡大学)

Da Li, Jianshu Zhang, Yongxin Yang, Cong Liu, Yi-Zhe Song, Timothy M. Hospedales

摘要:

领域泛化(Domain Generalization,DG)是学习模型的一个具有挑战性和热点的问题,它可以推广到新的测试领域,而不是一组已知的训练领域。聚合来自所有源域的数据并对所有数据进行端到端训练单个深度神经网络的简单方法提供了一个令人惊讶的强大基线,超过了许多先前发布的方法。在本文中,我们在这一强基线的基础上设计了一个情景训练过程,该过程以一种方式训练单个深度网络,使其在运行时暴露于新领域特征的领域转变。具体来说,我们将深度网络分解为特征提取器和分类器组件,然后通过模拟每个组件与一个针对当前域调整得很差的合作伙伴进行交互来训练每个组件。这使得这两个组件更加强大,最终导致我们的网络在三个DG基准上产生最先进的性能。此外,我们考虑使用ImageNet训练的CNN作为下游识别任务的固定特征提取器的普遍工作流程。使用Visual Decathlon基准测试,我们证明了我们的episodic-DG训练通过显式训练新问题的鲁棒性特征来提高这种通用特征提取器的性能。这表明DG训练可以有益于计算机视觉中的标准实践。

英文摘要:

Domain generalization (DG) is the challenging and topical problem of learning models that generalize to novel testing domains with different statistics than a set of known training domains. The simple approach of aggregating data from all source domains and training a single deep neural network end-to-end on all the data provides a surprisingly strong baseline that surpasses many prior published methods. In this paper, we build on this strong baseline by designing an episodic training procedure that trains a single deep network in a way that exposes it to the domain shift that characterises a novel domain at runtime. Specifically, we decompose a deep network into feature extractor and classifier components, and then train each component by simulating it interacting with a partner who is badly tuned for the current domain. This makes both components more robust, ultimately leading to our networks producing state-of-the-art performance on three DG benchmarks. Furthermore, we consider the pervasive workflow of using an ImageNet trained CNN as a fixed feature extractor for downstream recognition tasks. Using the Visual Decathlon benchmark, we demonstrate that our episodic-DG training improves the performance of such a general-purpose feature extractor by explicitly training a feature for robustness to novel problems. This shows that DG training can benefit standard practice in computer vision.

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。

↑