arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1802.03601cs.CV
收藏

深度视觉领域自适应研究综述

Deep Visual Domain Adaptation: A Survey

Beijing University of Posts and Telecommunications(北京邮电大学)

Mei Wang, Weihong Deng

摘要:

深度域自适应已经成为一种新的学习技术,以解决缺乏大量标记数据的问题。与学习共享特征子空间或重用具有浅表示的重要源实例的传统方法相比,深度域自适应方法通过在深度学习的流水线中嵌入领域自适应来利用深度网络来学习更多可传递的表示。对于浅域适应已经有了全面的调查,但是很少有及时的评论新兴的基于深度学习的方法。在本文中,我们提供了一个全面的调查深领域自适应方法的计算机视觉的应用有四个主要贡献。首先,我们根据定义两个域如何分叉的数据属性,提出了不同深度域自适应场景的分类。其次,我们总结了几类基于训练损失的深度域自适应方法,并简要分析和比较了这些类别下的最先进的方法。第三,我们概述了计算机视觉在图像分类之外的应用,如人脸识别、语义分割和目标检测。第四,目前的方法和未来的几个方向的一些潜在的不足之处突出。

英文摘要:

Deep domain adaption has emerged as a new learning technique to address the lack of massive amounts of labeled data. Compared to conventional methods, which learn shared feature subspaces or reuse important source instances with shallow representations, deep domain adaption methods leverage deep networks to learn more transferable representations by embedding domain adaptation in the pipeline of deep learning. There have been comprehensive surveys for shallow domain adaption, but few timely reviews the emerging deep learning based methods. In this paper, we provide a comprehensive survey of deep domain adaptation methods for computer vision applications with four major contributions. First, we present a taxonomy of different deep domain adaption scenarios according to the properties of data that define how two domains are diverged. Second, we summarize deep domain adaption approaches into several categories based on training loss, and analyze and compare briefly the state-of-the-art methods under these categories. Third, we overview the computer vision applications that go beyond image classification, such as face recognition, semantic segmentation and object detection. Fourth, some potential deficiencies of current methods and several future directions are highlighted.

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。

↑