首页> 外文期刊>Neural Networks and Learning Systems, IEEE Transactions on >Heterogeneous Domain Adaptation Through Progressive Alignment
【24h】

Heterogeneous Domain Adaptation Through Progressive Alignment

机译:通过逐步比对的异构域适应

获取原文
获取原文并翻译 | 示例

摘要

In real-world transfer learning tasks, especially in cross-modal applications, the source domain and the target domain often have different features and distributions, which are well known as the heterogeneous domain adaptation (HDA) problem. Yet, existing HDA methods focus on either alleviating the feature discrepancy or mitigating the distribution divergence due to the challenges of HDA. In fact, optimizing one of them can reinforce the other. In this paper, we propose a novel HDA method that can optimize both feature discrepancy and distribution divergence in a unified objective function. Specifically, we present progressive alignment, which first learns a new transferable feature space by dictionary-sharing coding, and then aligns the distribution gaps on the new space. Different from previous HDA methods that are limited to specific scenarios, our approach can handle diverse features with arbitrary dimensions. Extensive experiments on various transfer learning tasks, such as image classification, text categorization, and text-to-image recognition, verify the superiority of our method against several state-of-the-art approaches.
机译:在实际的迁移学习任务中,尤其是在跨模式应用程序中,源域和目标域通常具有不同的功能和分布,这就是众所周知的异构域适应(HDA)问题。然而,由于HDA的挑战,现有的HDA方法着重于减轻特征差异或减轻分布差异。实际上,优化其中一个可以增强另一个。在本文中,我们提出了一种新的HDA方法,该方法可以在统一目标函数中同时优化特征差异和分布差异。具体来说,我们介绍渐进式对齐,它首先通过字典共享编码学习新的可转移特征空间,然后对齐新空间上的分布间隙。与以前的HDA方法(仅限于特定场景)不同,我们的方法可以处理任意尺寸的各种功能。在各种转移学习任务(例如图像分类,文本分类和文本到图像识别)上的大量实验,证明了我们的方法相对于几种最新方法的优越性。

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