arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2212.07101cs.CVcs.LG
收藏

基于学习和去除领域特征的领域泛化

Domain Generalization by Learning and Removing Domain-specific Features

University of Wollongong(伍伦贡大学);University of Technology Sydney(悉尼科技大学)

Yu Ding, Lei Wang, Bin Liang, Shuming Liang, Yang Wang, Fang Chen

摘要:

当测试数据集遵循与训练数据集不同的分布时,深度神经网络(DNN)会发生域偏移。领域泛化旨在通过学习可以泛化到未知领域的模型来解决这个问题。在本文中,我们提出了一种新的方法,旨在明确地删除特定领域的领域泛化功能。根据这种方法,我们提出了一种新的框架,称为学习和删除特定领域的特征泛化(LRDG),通过从输入图像中策略性地删除特定领域的特征来学习域不变模型。具体来说,我们设计了一个分类器,以有效地学习每个源域的特定领域的功能,分别。然后,我们开发了一个编码器-解码器网络,将每个输入图像映射到一个新的图像空间,在这个空间中,学习到的特定于领域的特征被删除。利用编解码器网络输出的图像,设计另一个分类器学习域不变特征进行图像分类。大量的实验表明,我们的框架实现了优越的性能相比,国家的最先进的方法。

英文摘要:

Deep Neural Networks (DNNs) suffer from domain shift when the test dataset follows a distribution different from the training dataset. Domain generalization aims to tackle this issue by learning a model that can generalize to unseen domains. In this paper, we propose a new approach that aims to explicitly remove domain-specific features for domain generalization. Following this approach, we propose a novel framework called Learning and Removing Domain-specific features for Generalization (LRDG) that learns a domain-invariant model by tactically removing domain-specific features from the input images. Specifically, we design a classifier to effectively learn the domain-specific features for each source domain, respectively. We then develop an encoder-decoder network to map each input image into a new image space where the learned domain-specific features are removed. With the images output by the encoder-decoder network, another classifier is designed to learn the domain-invariant features to conduct image classification. Extensive experiments demonstrate that our framework achieves superior performance compared with state-of-the-art methods.

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。

↑