arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1709.08128cs.CV
收藏

约束深度迁移特征学习及其应用

Constrained Deep Transfer Feature Learning and its Applications

Rensselaer Polytechnic Institute(伦斯勒理工学院)

Yue Wu, Qiang Ji

摘要:

使用深度模型的特征学习在各种视觉任务的数据表示和分类方面都取得了令人印象深刻的结果。然而,深度特征学习通常需要大量的训练数据,这对于某些应用领域可能是不可行的。迁移学习可以通过将数据从数据丰富的源域迁移到数据稀缺的目标域来缓解这一问题。现有的迁移学习方法通常执行一次性迁移学习,并且经常忽略所传输的数据必须满足的特定属性。为了解决这些问题,我们引入了一种受约束的深度迁移特征学习方法,通过在逐步改进的特征空间中迭代地执行迁移学习来同时执行迁移学习和特征学习,以便更好地缩小目标域和源域之间的差距,从而将数据从源域有效地迁移到目标域。此外,我们建议利用目标领域的知识,并将这种先验知识作为迁移学习过程中的约束,以确保传输的数据满足目标领域的某些属性。为了证明所提出的约束深度转移特征学习方法的有效性,我们将其应用于通过从可见域转移来进行眼睛检测的热特征学习。我们还将所提出的方法用于跨视图面部表情识别作为第二个应用程序。实验结果表明,该方法的有效性,这两个应用程序。

英文摘要:

Feature learning with deep models has achieved impressive results for both data representation and classification for various vision tasks. Deep feature learning, however, typically requires a large amount of training data, which may not be feasible for some application domains. Transfer learning can be one of the approaches to alleviate this problem by transferring data from data-rich source domain to data-scarce target domain. Existing transfer learning methods typically perform one-shot transfer learning and often ignore the specific properties that the transferred data must satisfy. To address these issues, we introduce a constrained deep transfer feature learning method to perform simultaneous transfer learning and feature learning by performing transfer learning in a progressively improving feature space iteratively in order to better narrow the gap between the target domain and the source domain for effective transfer of the data from the source domain to target domain. Furthermore, we propose to exploit the target domain knowledge and incorporate such prior knowledge as a constraint during transfer learning to ensure that the transferred data satisfies certain properties of the target domain. To demonstrate the effectiveness of the proposed constrained deep transfer feature learning method, we apply it to thermal feature learning for eye detection by transferring from the visible domain. We also applied the proposed method for cross-view facial expression recognition as a second application. The experimental results demonstrate the effectiveness of the proposed method for both applications.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑