...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Neurocomputing >Domain-invariant representation learning using an unsupervised domain adversarial adaptation deep neural network
【24h】

Domain-invariant representation learning using an unsupervised domain adversarial adaptation deep neural network

机译：使用无监督领域对抗性适应性深度神经网络的领域不变表示学习

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Domain adaptation is proposed to improve the recognition performance of the domain shift or the dataset bias. The domain shift is a very common problem, which is caused by diverse factors, such as data capturing angles, illumination, and image quality existing in the natural scene image understanding. Since the domain shift leads to the feature distribution discrepancy, some solutions have been proposed to alleviate the distribution discrepancy by mapping feature spaces between source and target domains, so as to ensure the transferable features can be learned by the deep networks during the end-to-end training for the classification tasks. However, it is still a big challenge to address the domain shift when the distribution spaces are not clearly separated. Inspired by the adversarial idea, we propose a novel unified deep neural network architecture named the unsupervised domain adversarial adaptation deep neural network. It addresses the domain adaptation problem by learning domain-invariant features through mitigating the feature discriminative ability in the domain classification task alternatively by alleviating the feature distribution discrepancy in the main classification task. Therefore, in our proposed unified deep network, we integrate two main modules. One is an auxiliary task module for the domain classifier, which is trained to make sure the learned features are domain-invariant under the adversarial optimization strategy by minimizing the domain discriminative ability. The other is the module at task-specific layers to enhance the learning of the transferable features with the less distribution discrepancy by adding multiple maximum mean discrepancy constraints to map the features to reproducing kernel Hilbert spaces. The experimental results show that the features learned by our proposed unified deep neural network perform better than the features learned by previous cross-domain neural networks on classification tasks. Our proposed approach achieves the state-of-the-art performance on three cross-domain datasets: Office-31 (different capturing angles, illumination, and image quality), Office-Caltech (modified from Office-31) and a combined cross-domain digit dataset, including MNIST, USPS and SVHN (different style digits in each dataset). (C) 2019 Elsevier B.V. All rights reserved.
机译：提出域自适应以提高域移位或数据集偏差的识别性能。域偏移是一个非常普遍的问题，它是由多种因素引起的，例如自然场景图像理解中存在的数据捕获角度，照明和图像质量。由于域移位导致特征分布差异，因此提出了一些解决方案，通过在源域和目标域之间映射特征空间来缓解分布差异，从而确保深层网络可以在端到端学习到可传递的特征。结束分类任务的培训。但是，当分布空间没有明确分开时，解决域转移仍然是一个很大的挑战。受对抗思想的启发，我们提出了一种新颖的统一深度神经网络架构，称为无监督域对抗适应深度神经网络。它通过减轻域分类任务中的特征判别能力来学习域不变特征，或者通过减轻主分类任务中的特征分布差异来解决域不变性问题。因此，在我们提出的统一深度网络中，我们集成了两个主要模块。一个是用于领域分类器的辅助任务模块，该任务模块经过训练以通过最小化领域判别能力来确保在对抗性优化策略下学习的特征是领域不变的。另一个是任务特定层的模块，它通过添加多个最大平均差异约束以将特征映射到再现内核希尔伯特空间，从而以较小的分布差异来增强可转让特征的学习。实验结果表明，我们提出的统一深度神经网络所学习的特征在分类任务上的性能优于以前的跨域神经网络所学习的特征。我们提出的方法可在三个跨域数据集上实现最先进的性能：Office-31（不同的捕获角度，照度和图像质量），Office-Caltech（从Office-31修改）和组合的跨域数据集域数字数据集，包括MNIST，USPS和SVHN（每个数据集中的不同样式数字）。 （C）2019 Elsevier B.V.保留所有权利。

著录项

  • 来源
    《Neurocomputing》 |2019年第25期|209-220|共12页
  • 作者

    Jia Xibin; Jin Ya; Su Xing; Hu Yongli;

  • 作者单位

    Beijing Univ Technol, Fac Informat Technol, Beijing 100124, Peoples R China|Beijing Univ Technol, Fac Informat Technol, Beijing Municipal Key Lab Multimedia & Intelligen, Beijing, Peoples R China;

    Beijing Univ Technol, Fac Informat Technol, Beijing 100124, Peoples R China;

    Beijing Univ Technol, Fac Informat Technol, Beijing 100124, Peoples R China;

    Beijing Univ Technol, Fac Informat Technol, Beijing 100124, Peoples R China|Beijing Univ Technol, Fac Informat Technol, Beijing Municipal Key Lab Multimedia & Intelligen, Beijing, Peoples R China;

  • 收录信息 美国《科学引文索引》(SCI);美国《工程索引》(EI);
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类
  • 关键词

    Domain adaptation; Feature distribution discrepancy; Domain-invariant feature; Unsupervised adversarial network; Unified deep neural network;

    机译：域适应;特征分布差异;域不变特征;无监督对抗网络;统一深度神经网络;

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号