arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2012.14176cs.CV
收藏

深度视觉领域自适应

Deep Visual Domain Adaptation

Naver Labs Europe(NAVER 欧洲实验室)

Gabriela Csurka

摘要:

领域自适应(DA)是通过迁移源领域中的知识来提高模型在目标领域上的性能。随着深度学习模型的最新进展,在过去的十年中,对视觉DA的兴趣显着增加,该领域的相关工作数量激增。因此,本文的目的是全面概述计算机视觉应用的深度领域自适应方法。首先,我们详细介绍并比较了利用深层架构进行领域自适应的不同可能方法。然后,我们提出了一个概述最近的趋势,在深度视觉DA。最后,我们提到了一些改进策略,正交这些方法,可以应用于这些模型。虽然我们主要集中在图像分类,我们给指针的论文,扩展这些想法的其他应用程序,如语义分割,目标检测,人重新识别,和其他人。

英文摘要:

Domain adaptation (DA) aims at improving the performance of a model on target domains by transferring the knowledge contained in different but related source domains. With recent advances in deep learning models which are extremely data hungry, the interest for visual DA has significantly increased in the last decade and the number of related work in the field exploded. The aim of this paper, therefore, is to give a comprehensive overview of deep domain adaptation methods for computer vision applications. First, we detail and compared different possible ways of exploiting deep architectures for domain adaptation. Then, we propose an overview of recent trends in deep visual DA. Finally, we mention a few improvement strategies, orthogonal to these methods, that can be applied to these models. While we mainly focus on image classification, we give pointers to papers that extend these ideas for other applications such as semantic segmentation, object detection, person re-identifications, and others.

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。

↑