• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Neural Networks and Learning Systems, IEEE Transactions on >Feature Analysis of Marginalized Stacked Denoising Autoenconder for Unsupervised Domain Adaptation
【24h】

Feature Analysis of Marginalized Stacked Denoising Autoenconder for Unsupervised Domain Adaptation

机译：无监督域适应的边缘化堆积自动化器的特征分析

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

Marginalized stacked denoising autoencoder (mSDA), has recently emerged with demonstrated effectiveness in domain adaptation. In this paper, we investigate the rationale for why mSDA benefits domain adaptation tasks from the perspective of adaptive regularization. Our investigations focus on two types of feature corruption noise: Gaussian noise (mSDA(g)) and Bernoulli dropout noise (mSDA(bd)). Both theoretical and empirical results demonstrate that mSDA(bd) successfully boosts the adaptation performance but mSDA(g) fails to do so. We then propose a new mSDA with data-dependent multinomial dropout noise (mSDA(md)) that overcomes the limitations of mSDA(bd) and further improves the adaptation performance. Our mSDA(md) is based on a more realistic assumption: different features are correlated and, thus, should be corrupted with different probabilities. Experimental results demonstrate the superiority of mSDA(md) to mSDA(bd) on the adaptation performance and the convergence speed. Finally, we propose a deep transferable feature coding (DTFC) framework for unsupervised domain adaptation. The motivation of DTFC is that mSDA fails to consider the distribution discrepancy across different domains in the feature learning process. We introduce a new element to mSDA: domain divergence minimization by maximum mean discrepancy. This element is essential for domain adaptation as it ensures the extracted deep features to have a small distribution discrepancy. The effectiveness of DTFC is verified by extensive experiments on three benchmark data sets for both Bernoulli dropout noise and multinomial dropout noise.
机译：最近出现了边缘化的堆积自动化器（MSDA），展示了域适应的有效性。在本文中，我们调查了为什么MSDA从自适应正规化视角下汲取域适应任务的理由。我们的调查专注于两种类型的特征损坏噪声：高斯噪声（MSDA（G））和伯努利丢失噪声（MSDA（BD））。理论和经验结果都表明MSDA（BD）成功提升了适应性能，但MSDA（G）未能这样做。然后，我们提出了一种新的MSDA，具有克服MSDA（BD）的限制并进一步提高适应性能的数据相关的多项丢失噪声（MSDA（MD））。我们的MSDA（MD）基于更现实的假设：不同的功能是相关的，因此应该用不同的概率损坏。实验结果证明了MSDA（MD）对MSDA（BD）的优越性，适应性能和收敛速度。最后，我们为无监督域适应提出了一个深度可转移的特征编码（DTFC）框架。 DTFC的动机是MSDA未能考虑特征学习过程中不同域中的分布差异。我们向MSDA引入一个新的元素：通过最大均值差异来最小化域分歧。此元素对于域适配至关重要，因为它确保提取的深度特征具有小的分布差异。在Bernoulli丢失噪声和多项辍学噪声的三个基准数据集中，DTFC的有效性被广泛的实验验证。

著录项

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