arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2201.01002cs.CVcs.AIcs.LG
收藏

跨域图像分类的多表示自适应网络

Multi-Representation Adaptation Network for Cross-domain Image Classification

Key Lab of Intelligent Information Processing of Chinese Academy of Sciences (CAS), Institute of Computing Technology, CAS(中国科学院智能信息处理重点实验室,中国科学院计算技术研究所);University of Chinese Academy of Sciences(中国科学院大学);Microsoft Research(微软研究院);Capital Normal University(首都师范大学);ByteDance(字节跳动);School of Information, Renmin University of China(中国人民大学信息学院)

Yongchun Zhu, Fuzhen Zhuang, Jindong Wang, Jingwu Chen, Zhiping Shi, Wenjuan Wu, Qing He

摘要:

在图像分类中,获取足够的标签通常是昂贵且耗时的。为了解决这个问题,领域自适应通常提供了一个有吸引力的选择,给出了大量的标记数据从一个类似的性质,但不同的域。现有的方法主要对齐由单个结构提取的表示的分布,并且表示可能仅包含部分信息,例如,仅包含部分饱和度、亮度和色调信息。沿着这条线,我们提出了多表示自适应,它可以显着提高跨域图像分类的分类精度,特别是旨在对齐的混合结构名为初始自适应模块(IAM)提取的多个表示的分布。在此基础上,本文提出了多表示自适应网络(MRAN),通过多表示对齐来实现跨域图像分类任务。此外,我们扩展了最大平均离散(MMD)计算自适应损失。我们的方法可以很容易地实现,通过扩展大多数前馈模型与IAM,网络可以通过反向传播有效地训练。在三个基准图像数据集上进行的实验证明了MRAN的有效性。该代码已在https://github.com/easezyc/deep-transfer-learning上提供。

英文摘要:

In image classification, it is often expensive and time-consuming to acquire sufficient labels. To solve this problem, domain adaptation often provides an attractive option given a large amount of labeled data from a similar nature but different domain. Existing approaches mainly align the distributions of representations extracted by a single structure and the representations may only contain partial information, e.g., only contain part of the saturation, brightness, and hue information. Along this line, we propose Multi-Representation Adaptation which can dramatically improve the classification accuracy for cross-domain image classification and specially aims to align the distributions of multiple representations extracted by a hybrid structure named Inception Adaptation Module (IAM). Based on this, we present Multi-Representation Adaptation Network (MRAN) to accomplish the cross-domain image classification task via multi-representation alignment which can capture the information from different aspects. In addition, we extend Maximum Mean Discrepancy (MMD) to compute the adaptation loss. Our approach can be easily implemented by extending most feed-forward models with IAM, and the network can be trained efficiently via back-propagation. Experiments conducted on three benchmark image datasets demonstrate the effectiveness of MRAN. The code has been available at https://github.com/easezyc/deep-transfer-learning.

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。

↑