...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Neural computing & applications >Deep joint two-stream Wasserstein auto-encoder and selective attention alignment for unsupervised domain adaptation
【24h】

Deep joint two-stream Wasserstein auto-encoder and selective attention alignment for unsupervised domain adaptation

机译：深关节双流Wasserstein自动编码器和无监督域适应的选择性注意对齐

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 refers to the process of utilizing the labeled source domain data to learn a model that can perform well in the target domain with limited or missing labels. Several domain adaptation methods combining image translation and feature alignment have been recently proposed. However, there are two primary drawbacks of such methods. First, the majority of the methods assume that synthetic target images have the same distribution as real target images, and thus, only the synthetic target images are employed for training the target classifier, which makes the model's performance significantly dependent on the quality of the generated images. Second, most of the methods blindly align the discriminative content information by merging spatial and channel-wise information, thereby ignoring the relationships among channels. To address these issues, a two-step approach that joints two-stream Wasserstein auto-encoder (WAE) and selective attention (SA) alignment, named J2WSA, is proposed in this study. In the pre-training step, the two-stream WAE is employed for mapping the four domains to a shared nice manifold structure by minimizing the Wasserstein distance between the distribution of each domain and the corresponding prior distribution. During the fine-tuning step, the SA alignment model initialized by the two-stream WAE is applied for automatically selecting the style part of channels for alignment, while simultaneously suppressing the content part alignment using the SA block. Extensive experiments indicate that the combination of the aforementioned two models can achieve state-of-the-art performance on the Office-31 and digital domain adaptation benchmarks.
机译：域适应是指利用标记的源域数据来学习在具有有限或缺少标签的目标域中可以良好执行的模型。最近提出了几种域适应方法，结合了图像转换和特征对准。然而，这些方法存在两个主要缺点。首先，这些方法的大多数假设合成目标图像具有与真实目标图像相同的分布，因此，仅采用合成目标图像训练目标分类器，这使得模型的性能显着取决于所生成的质量图片。其次，大多数方法通过合并空间和通道的信息来盲目地对准辨别内容信息，从而忽略频道之间的关系。为解决这些问题，在本研究中提出了一种两步的方法，即在本研究中提出了名为J2WSA的双流Wasserstein自动编码器（WAE）和选择性注意（SA）对齐。在预训练步骤中，通过最小化每个域的分布和相应的先前分布之间的Wassersein距离，使用两流焊接来将四个域映射到共享的漂亮歧管结构。在微调步骤期间，通过两个流焊缝初始化的SA对准模型用于自动选择用于对齐的通道的风格部分，同时使用SA块抑制内容部分对齐。广泛的实验表明，上述两种模型的组合可以在Office-31和数字域适应基准上实现最先进的性能。

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