arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2211.04582cs.LG
收藏

用于领域泛化的领域不变参数学习

Learning to Learn Domain-invariant Parameters for Domain Generalization

Institute of Computing Technology, Chinese Academy of Sciences(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);Southeast University(东南大学);Lenovo Research(联想研究院);Lenovo Ltd(联想有限公司)

Feng Hou, Yao Zhang, Yang Liu, Jin Yuan, Cheng Zhong, Yang Zhang, Zhongchao Shi, Jianping Fan, Zhiqiang He

摘要:

在实际应用中,由于域转移的影响,深度神经网络(DNN)通常不能很好地泛化未知的测试数据。领域泛化(DG)的目的是克服这个问题,从源域捕获域不变的表示。基于DNN的部分参数被优化以提取域不变表示的见解,我们期望一个能够很好地感知和重点更新这些域不变参数的通用模型。在本文中,我们提出了两个模块的域解耦和组合(DDC)和域不变性引导反向传播(DIGB),这可以鼓励这样的一般模型专注于参数,有一个统一的优化方向对对比样本。我们在两个基准上的大量实验表明,我们提出的方法具有很强的泛化能力,达到了最先进的性能。

英文摘要:

Due to domain shift, deep neural networks (DNNs) usually fail to generalize well on unknown test data in practice. Domain generalization (DG) aims to overcome this issue by capturing domain-invariant representations from source domains. Motivated by the insight that only partial parameters of DNNs are optimized to extract domain-invariant representations, we expect a general model that is capable of well perceiving and emphatically updating such domain-invariant parameters. In this paper, we propose two modules of Domain Decoupling and Combination (DDC) and Domain-invariance-guided Backpropagation (DIGB), which can encourage such general model to focus on the parameters that have a unified optimization direction between pairs of contrastive samples. Our extensive experiments on two benchmarks have demonstrated that our proposed method has achieved state-of-the-art performance with strong generalization capability.

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。

↑