Deep Visual Domain Adaptation: A Survey 深度域适应:调研

论文地址: https://arxiv.org/abs/1802.03601

四个主要贡献。

首先,根据定义两个域如何分歧的数据属性,提出不同深度域适应场景的分类。

其次,基于训练损失将深度域适应方法概括为几个类别,并分析和比较这些类别下的最新方法。

第三,概述了超越图像分类的计算机视觉应用,例如人脸识别,语义分割和对象检测。

第四,强调了当前方法的一些潜在缺陷和未来的几个方向。

Domain adaption 分类

深度域适应

广义:使用了深度特征的浅层方法也属于深度方法

狭义:将DA嵌入深度特征表示的学习过程中

A:One-Step Domain Adaption

1

类标准:使用标签信息作为引领,在不同领域之间传输知识

统计标准: 使用一些数学方法进行数据分布的变化,通常使用MMD,CORAL,KL等

架构标准: 利用深度网络学习更多的可迁移的特征

几何标准: 利用几何特征把源域和目标域结合起来

2基于对抗网络的DA,让网络分不清你到底是从属于源域还是目标域,以减少两个域映射分布的距离

生成模型: GAN  使用源图片,噪音生成人造的目标域样例,同时保留源域注释信息

非生成模型: 特征提取器使用源域中的类信息提取一个特征,同时使用domain-confusion loss把目

标域映射到同一个特征空间

3基于重建的网络

GAN描述重建样例和图片之间的差异(重建误差)

 

  • 1
    点赞
  • 0
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
Domain adaptation is an active, emerging research area that attempts to address the changes in data distribution across training and testing datasets. With the availability of a multitude of image acquisition sen- sors, variations due to illumination, and viewpoint among others, com- puter vision applications present a very natural test bed for evaluating domain adaptation methods. In this monograph, we provide a compre- hensive overview of domain adaptation solutions for visual recognition problems. By starting with the problem description and illustrations, we discuss three adaptation scenarios namely, (i) unsupervised adap- tation where the “source domain” training data is partially labeled and the “target domain” test data is unlabeled, (ii) semi-supervised adaptation where the target domain also has partial labels, and (iii) multi-domain heterogeneous adaptation which studies the previous two settings with the source and/or target having more than one domain, and accounts for cases where the features used to represent the data in each domain are different. For all these topics we discuss existing adaptation techniques in the literature, which are motivated by the principles of max-margin discriminative learning, manifold learning, sparse coding, as well as low-rank representations. These techniques have shown improved performance on a variety of applications such as object recognition, face recognition, activity analysis, concept clas- sification, and person detection. We then conclude by analyzing the challenges posed by the realm of “big visual data”, in terms of the generalization ability of adaptation algorithms to unconstrained data acquisition as well as issues related to their computational tractability, and draw parallels with the efforts from vision community on image transformation models, and invariant descriptors so as to facilitate im- proved understanding of vision problems under uncertainty.

“相关推荐”对你有帮助么?

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值