跳到主要导航 跳到搜索 跳到主要内容

Joint Learning of Multiple Latent Domains and Deep Representations for Domain Adaptation

  • Xinxiao Wu*
  • , Jin Chen
  • , Feiwu Yu
  • , Mingyu Yao
  • , Jiebo Luo
  • *此作品的通讯作者
  • Beijing Institute of Technology
  • University of Rochester

科研成果: 期刊稿件 › 文章 › 同行评审

摘要

In domain adaptation, the automatic discovery of multiple latent source domains has succeeded by capturing the intrinsic structure underlying the source data. Different from previous works that mainly rely on shallow models for domain discovery, we propose a novel unified framework based on deep neural networks to jointly address latent domain prediction from source data and deep representation learning from both source and target data. Within this framework, an iterative algorithm is proposed to alternate between 1) utilizing a new probabilistic hierarchical clustering method to separate the source domain into latent clusters and 2) training deep neural networks by using the domain membership as the supervision to learn deep representations. The key idea behind this joint learning framework is that good representations can help to improve the prediction accuracy of latent domains and, in turn, domain prediction results can provide useful supervisory information for feature learning. During the training of the deep model, a domain prediction loss, a domain confusion loss, and a task-specific classification loss are effectively integrated to enable the learned feature to distinguish between different latent source domains, transfer between source and target domains, and become semantically meaningful among different classes. Trained in an end-to-end fashion, our framework outperforms the state-of-the-art methods for latent domain discovery, as validated by extensive experiments on both object classification and human action-recognition tasks.

源语言英语
期刊论文编号8745500
页(从-至)2676-2687
页数12
期刊IEEE Transactions on Cybernetics
卷51
期5
DOI
出版状态已出版 - 5月 2021

学术指纹

探究 'Joint Learning of Multiple Latent Domains and Deep Representations for Domain Adaptation' 的科研主题。它们共同构成独一无二的学术指纹。

引用此