首页> 外文期刊>Neural Networks and Learning Systems, IEEE Transactions on >Deep Subdomain Adaptation Network for Image Classification
【24h】

Deep Subdomain Adaptation Network for Image Classification

机译:深度子域适应网络用于图像分类

获取原文
获取原文并翻译 | 示例

摘要

For a target task where the labeled data are unavailable, domain adaptation can transfer a learner from a different source domain. Previous deep domain adaptation methods mainly learn a global domain shift, i.e., align the global source and target distributions without considering the relationships between two subdomains within the same category of different domains, leading to unsatisfying transfer learning performance without capturing the fine-grained information. Recently, more and more researchers pay attention to subdomain adaptation that focuses on accurately aligning the distributions of the relevant subdomains. However, most of them are adversarial methods that contain several loss functions and converge slowly. Based on this, we present a deep subdomain adaptation network (DSAN) that learns a transfer network by aligning the relevant subdomain distributions of domain-specific layer activations across different domains based on a local maximum mean discrepancy (LMMD). Our DSAN is very simple but effective, which does not need adversarial training and converges fast. The adaptation can be achieved easily with most feedforward network models by extending them with LMMD loss, which can be trained efficiently via backpropagation. Experiments demonstrate that DSAN can achieve remarkable results on both object recognition tasks and digit classification tasks. Our code will be available at https://github.com/easezyc/deep-transfer-learning.
机译:对于标记数据不可用的目标任务,域适应可以从不同的源域传输学习者。之前的深度域适应方法主要学习全局域移位,即,对齐全局源和目标分布,而不考虑不同域中的两个子域之间的关系,导致不满意的传输学习性能而不捕获细粒度信息。最近,越来越多的研究人员关注子域适应,专注于准确地对准相关子域的分布。然而,大多数是含有几种损失功能并缓慢收敛的侵扰方法。基于此,我们介绍了一个深度子域适应网络(DSAN),其通过基于局部最大平均差异(LMMD)对齐不同域的相关子域分布在不同域中的相关子域分布来学习传输网络。我们的DSAN非常简单但有效,这不需要对抗性培训和快速收敛。通过使用LMMD损耗将它们扩展,可以通过大多数前馈网络模型来容易地实现自适应,这可以通过BackProjagation有效地培训。实验表明,DSAN可以在对象识别任务和数字分类任务上实现显着的结果。我们的代码将在https://github.com/easezyc/deep-transferning上提供。

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